Air conditioning equipment

Abstract

The invention provides air conditioning equipment. The air conditioning equipment comprises a carbon dioxide sensor and a processing device; the processing device comprises an analysis unit, a reconstruction unit and an identification unit; the analysis unit is configured to perform set wavelet transform analysis based on the original carbon dioxide concentration time sequence so as to execute multi-stage decomposition, and the original carbon dioxide concentration time sequence is decomposed into multi-stage approximate components and detail components; the reconstruction unit is configured to reconstruct and generate an effective carbon dioxide concentration time sequence after multi-stage decomposition; the recognition unit is configured to recognize the statistical characteristics of the effective carbon dioxide concentration time sequence and presume the scene type of the air-conditioned room according to the statistical characteristics of the effective carbon dioxide concentration time sequence. According to the method, the wavelet transform analysis technology and the statistical feature recognition technology are combined, accurate analysis and scene recognition of the carbon dioxide concentration time sequence in the air-conditioned room are achieved, and the method has the advantages of being good in real-time performance and high in accuracy and intelligent degree.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to an air conditioning device. Background Art

[0002] Indoor air quality is closely linked to people's lives. As modern buildings become increasingly airtight, natural ventilation between indoor and outdoor spaces deteriorates, making it difficult for pollutants from indoor sources to effectively diffuse, leading to deteriorating air quality. Carbon dioxide (CO2) concentration is a key air quality parameter. In poorly ventilated rooms with occupants, CO2 concentrations rise rapidly. When concentrations exceed 1000 ppm (parts per million), the human body may experience symptoms such as dizziness, fatigue, and difficulty concentrating. Therefore, maintaining indoor CO2 concentrations at a healthy level (e.g., below 1000 ppm) is crucial.

[0003] Buildings with better sealing usually need to improve air quality through mechanical ventilation systems, such as through fresh air systems that regularly exhaust indoor air to the outside and introduce fresh air to maintain the freshness of the indoor air, or use air purifiers to effectively remove carbon dioxide and other pollutants from the indoor air.

[0004] However, modern buildings vary in function, including classrooms, offices, restaurants, hospitals, and residences. These buildings all experience distinct patterns of CO2 concentration, making existing air conditioning systems unable to automatically identify these locations. Even with pre-configured intelligent control modes tailored to various scenarios, these still rely on manual configuration by operators and users, resulting in a relatively low level of intelligence. Summary of the Invention

[0005] In view of the problem that the air conditioning equipment in the prior art cannot automatically identify the type of application place and has a relatively low level of intelligence, the first aspect of the present invention designs and provides an air conditioning equipment.

[0006] The air conditioning equipment includes a carbon dioxide sensor; the carbon dioxide sensor is configured to obtain the real-time concentration of carbon dioxide in the air-conditioned room, record and generate a raw carbon dioxide concentration time series.

[0007] In one or more embodiments of the present application, the air conditioning equipment also includes a processing device, the processing device includes a parsing unit, a reconstruction unit and an identification unit; wherein the parsing unit is configured to perform a wavelet transform analysis set based on the original carbon dioxide concentration time series to perform multi-level decomposition to decompose the original carbon dioxide concentration time series into multi-level approximate components and detail components; the reconstruction unit is configured to reconstruct and generate an effective carbon dioxide concentration time series after the multi-level decomposition; the identification unit is configured to identify the statistical characteristics of the effective carbon dioxide concentration time series, and infer the scene type of the air-conditioned room based on the statistical characteristics of the effective carbon dioxide concentration time series.

[0008] In one or more embodiments of the present application, the processing device further includes an estimating unit configured to estimate, within a determination period, whether the statistical characteristics of the effective carbon dioxide concentration time series match a preset scenario type estimating condition set based on the statistical characteristics.

[0009] In one or more embodiments of the present application, the recognition unit infers that the effective carbon dioxide concentration time series is the corresponding scene type; wherein the duration of the original carbon dioxide concentration time series includes one or more determination cycles.

[0010] In one or more embodiments of the present application, the duration of the original carbon dioxide concentration time series includes multiple determination periods.

[0011] In one or more embodiments of the present application, the processing device further includes a recording unit, a reliability generation unit, and an output unit; wherein the recording unit is configured to record the number of determination cycles estimated to be corresponding scene types, the reliability generation unit is configured to generate the reliability of the corresponding scene type based on the number of determination cycles, the duration of the determination cycle, and the duration of the original carbon dioxide concentration time series, and the output unit is configured to select a scene type that matches the reliability condition based on a preset reliability estimation condition.

[0012] In one or more embodiments of the present application, the recognition unit infers that the selected scene type that matches the reliability condition is the scene type of an air-conditioned room.

[0013] In one or more embodiments of the present application, the output unit is further configured to pause outputting the inferred scene when multiple scene types matching the reliability condition are selected; and to use the selected scene type as the inferred scene when only one scene type matching the reliability condition is selected.

[0014] In one or more embodiments of the present application, the processing device also includes: an update unit; the update unit is configured to obtain the reliability of the corresponding scene type generated by the reliability generation unit once within each preset update cycle; the output unit is also configured to select the scene type that matches the reliability condition as the estimated scene based on the preset reliability inference condition according to the reliability of the corresponding scene type obtained by the update unit.

[0015] In one or more embodiments of the present application, the parsing unit is configured to perform a three-level decomposition based on a set wavelet transform analysis of the original carbon dioxide concentration time series, wherein the first level decomposition decomposes the original carbon dioxide concentration time series into a first approximate component and a first detail component; the second level decomposition decomposes the first approximate component into a second approximate component and a second detail component; and the third level decomposition decomposes the second approximate component into a third approximate component and a third detail component.

[0016] In one or more embodiments of the present application, the reconstruction unit is configured to perform the following steps to perform weighted reconstruction to generate an effective carbon dioxide concentration time series: obtain wavelet coefficients corresponding to a set wavelet transform analysis; assign a weight to each wavelet coefficient; multiply the wavelet coefficients by the corresponding weights respectively, and add the weighted wavelet coefficients; and reconstruct the sum of the weighted coefficients through an inverse wavelet transform to generate an effective carbon dioxide time series.

[0017] In one or more embodiments of the present application, the statistical features include: one or more of: mean value, rate of change, maximum value, minimum value, variance, autocorrelation coefficient, standard deviation, and fluctuation coefficient.

[0018] In one or more embodiments of the present application, the processing device further includes: a pre-processing unit configured to assign a data type label to the carbon dioxide concentration detection signal of the air-conditioned room acquired by the carbon dioxide sensor.

[0019] In one or more embodiments of the present application, the scene types include: classroom areas, office areas, dining area, medical area, residential public area and / or residential bedroom area.

[0020] This application combines wavelet transform analysis technology and statistical feature recognition technology to achieve accurate analysis and scene recognition of the carbon dioxide concentration time series in the air-conditioned room. By performing multi-level decomposition and reconstruction of the signal, noise and interference signals can be effectively removed and the signal quality can be improved. By performing statistical feature recognition on the effective carbon dioxide concentration time series, the scene type of the air-conditioned room can be accurately inferred, providing a reference basis for air conditioning. This application has the advantages of good real-time performance, high accuracy and intelligence.

[0021] Other features and advantages of the present application will become more apparent from the following detailed description when read in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0023] Figure 1 is a structural schematic block diagram of an air conditioning device provided by one or more embodiments of the present application;

[0024] Figure 2 is a structural schematic block diagram of a processing device in the air conditioning device provided by one or more embodiments of the present application;

[0025] Figure 3 is a structural schematic block diagram of a processing device in the air conditioning device provided by one or more embodiments of the present application;

[0026] Figure 4 is a structural schematic block diagram of a processing device in the air conditioning device provided by one or more embodiments of the present application;

[0027] Figure 5 is a structural schematic block diagram of a processing device in the air conditioning device provided by one or more embodiments of the present application;

[0028] Figure 6 is a structural schematic block diagram of a processing device in the air conditioning device provided by one or more embodiments of the present application;

[0029] Figure 7 is a signal flow diagram of the air conditioning device provided by one or more embodiments of the present application;

[0030] Figure 8 is one example of a time-frequency distribution diagram of a time sequence of an original carbon dioxide concentration in the air conditioning device provided by one or more embodiments of the present application;

[0031] Figure 9 is one example of a time-frequency distribution diagram of an approximate component signal CA3;

[0032] Figure 10 is one example of a time-frequency distribution diagram of a detail component signal CD1;

[0033] Figure 11 is one example of a time-frequency distribution diagram of a detail component signal CD2;

[0034] Figure 12 is an example of a time-frequency profile of a detail component signal CD3;

[0035] Figure 13 is a flowchart of reconstructing a time series of effective carbon dioxide concentration in an air conditioning device according to one or more embodiments of the present application;

[0036] In the figure: 1, air conditioning device; 10, carbon dioxide sensor; 20, processing device; 21, analysis unit; 22, reconstruction unit; 23, identification unit; 24, estimation unit; 25, recording unit; 26, reliability generation unit; 27, output unit; 28, update unit; 301, processor; 302, non-volatile memory; 303, volatile memory; 304, display device; 305, operation device; 306, communication interface; 307, drive device; 308, bus; 309, storage medium; 310, storage medium. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0038] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0039] The terms "first", "second", are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, "a plurality of" means two or more.

[0040] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0041] In the present invention, unless otherwise expressly specified or limited, a first feature being "above" or "below" a second feature may include the first and second features being in direct contact, or may include the first and second features being in contact not directly but through another feature therebetween. Moreover, a first feature being "above," "above," and "above" a second feature includes the first feature being directly above and obliquely above the second feature, or simply means that the first feature is at a higher level than the second feature. A first feature being "below," "below," and "below" a second feature includes the first feature being directly below and obliquely below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0042] The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numerals and reference letters in different examples, and such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and settings discussed. In addition, the present invention provides examples of various specific processes and materials, but those of ordinary skill in the art will appreciate the application of other processes and the use of other materials.

[0043] The air conditioning equipment provided by the present invention is introduced below. The air conditioning equipment provided by the present invention can improve the air quality and enhance the cleanliness, healthiness and comfort of the air.

[0044] In one or more embodiments of the present application, the air conditioning device 1 may be an air conditioner.

[0045] An air conditioner performs its refrigeration cycle by using a compressor, condenser, throttling element, and evaporator. The refrigeration cycle involves a series of processes involving compression, condensation, expansion, and evaporation to cool or heat the indoor space.

[0046] Low-temperature, low-pressure refrigerant enters the compressor, which compresses it into high-temperature, high-pressure refrigerant gas and discharges the compressed refrigerant gas. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, releasing heat into the surrounding environment through the condensation process.

[0047] The throttling element (e.g., an electronic expansion valve) expands the high-temperature, high-pressure liquid refrigerant condensed in the condenser to a low-pressure liquid. The evaporator evaporates the refrigerant expanded in the electronic expansion valve and returns the low-temperature, low-pressure refrigerant gas to the compressor. The evaporator achieves a cooling effect by utilizing the latent heat of evaporation to exchange heat with the material being cooled. Throughout this cycle, the air conditioner regulates the temperature of the indoor space.

[0048] The outdoor unit of the air conditioner refers to a portion of a refrigeration cycle including a compressor and an outdoor heat exchanger, the indoor unit of the air conditioner includes an indoor heat exchanger, and the electronic expansion valve may be provided in the indoor unit or the outdoor unit.

[0049] The indoor heat exchanger and the outdoor heat exchanger function as a condenser or an evaporator. When the indoor heat exchanger functions as a condenser, the air conditioner functions as a heater in heating mode, and when the indoor heat exchanger functions as an evaporator, the air conditioner functions as a cooler in cooling mode.

[0050] In one or more embodiments of the present application, the air conditioning device 1 may be a fresh air device. The fresh air device includes a filter and a fan, which are used to remove particulate matter and harmful gases from the air while introducing fresh air to maintain fresh indoor air. The fresh air device may be a standalone device or integrated into an air conditioner as a functional module of the air conditioner.

[0051] In one or more embodiments of the present application, the air conditioning device 1 may be an air purifier.

[0052] An air purifier is a device used to improve indoor air quality by removing particulate matter, gaseous pollutants and harmful substances in the air, as well as eliminating odors and killing bacteria, making the air fresher and healthier.

[0053] Air purifiers can be equipped with a filtration system to remove particulate matter from the air. The filtration system can be an HEPA (High Efficiency Particulate Air Filter), an activated carbon filter, or the like.

[0054] Air purifiers can also be equipped with ultraviolet lamps to kill bacteria, viruses and other microorganisms in the air.

[0055] An ion generator can also be installed in the air purifier to charge the particles in the air and make them easier to be captured by the filter.

[0056] In one or more embodiments of the present application, the air conditioning device 1 may be a total heat exchanger.

[0057] A heat exchanger can transfer heat between incoming and outgoing air, recovering energy and pre-conditioning the temperature of fresh air entering a building. This reduces the energy required for heating or air conditioning, lowering energy consumption and saving energy costs. A heat exchanger can also adjust humidity where appropriate, helping to maintain indoor air comfort and quality.

[0058] In one or more embodiments of the present application, the air conditioning device 1 may be a dehumidifier.

[0059] In one or more embodiments of the present application, the air conditioning device 1 may be a humidifier.

[0060] In one or more embodiments of the present application, the air conditioning device 1 may be an air circulation fan.

[0061] Air circulation fans are used to promote air movement, helping to evenly distribute airborne pollutants and temperature.

[0062] In one or more embodiments of the present application, the air conditioning equipment 1 may also be a combination of multiple air conditioners, fresh air equipment, air purifiers, full heat exchangers, dehumidifiers, humidifiers, and air circulation fans.

[0063] The air conditioning device 1 includes a carbon dioxide sensor 10. The carbon dioxide sensor 10 is configured to obtain the real-time carbon dioxide concentration in the air-conditioned room, record and generate a raw carbon dioxide concentration time series.

[0064] In one or more embodiments of the present application, the carbon dioxide concentration sensor can be a sensor based on non-scattering infrared absorption (N DI R). The N DI R sensor uses the property of carbon dioxide absorbing light under infrared light of a specific wavelength, and reduces the calculated carbon dioxide concentration by measuring the intensity of the infrared light after passing through the air sample.

[0065] In one or more embodiments of the present application, the carbon dioxide concentration sensor may also be an electrochemical sensor, i.e., a sensor that detects carbon dioxide concentration using an electrochemical reaction. When carbon dioxide molecules react with the electrochemical material on the sensor surface, an electrical signal is generated, the magnitude of which is uniquely related to the carbon dioxide concentration.

[0066] In one or more embodiments of the present application, the carbon dioxide concentration sensor may also detect the carbon dioxide concentration by utilizing the effect of carbon dioxide molecules on temperature.

[0067] In one or more embodiments of the present application, the carbon dioxide concentration sensor may also utilize spectral analysis technology to detect the carbon dioxide concentration.

[0068] The carbon dioxide concentration sensor can also detect the carbon dioxide concentration based on other principles.

[0069] like Figure 1 As shown, the air conditioning device 1 further comprises a processing device 20 .

[0070] Figure 3 This is a block diagram showing the structure of the hardware structure of the processing device 20. The processing device 20 includes components such as a processor 301, a volatile memory 303, a non-volatile memory 302, a display device 304, an operating device 305, a communication interface 306, and a drive device 307, which are interconnected via a bus 308. The processor 301 can be a dedicated processor 301, a central processing unit 20 (CPU), etc. The processor 301 can access the storage unit to execute instructions or applications stored in the storage unit to implement related functions. The display device is a display device for displaying various information, the operating device is an operating device for receiving various operations, and the drive device is a hardware terminal that interacts with the storage medium. In one or more embodiments of the present application, the storage medium (as shown in 310 in the figure) includes a medium that records information optically, electrically or magnetically, such as a CD-ROM, a floppy disk, or a magneto-optical disk. The storage medium (as shown in 309 in the figure) can also be a semiconductor memory that records information electrically, such as a ROM or flash memory.

[0071] The processing device 20 may be a controller of the air conditioning device 1 itself, such as a system on board built based on an MCU.

[0072] The processing device 20 may also be a host computer or a cloud server, or other intelligent mobile terminal. The processing device 20 and the detection device may be connected via a LAN (Local Area Network), a signal line (such as an Ethernet cable, a coaxial cable, an optical fiber, a power line, a serial port line, etc.), a wireless signal, LTE, 5G, or other network connection to enable communication.

[0073] The following is the attached Figures 2 to 6 , the functional structure of the processing device 20 is explained.

[0074] like Figure 2As shown, in one or more embodiments of the present application, the processing device 20 includes a parsing unit 21, a reconstruction unit 22, and a recognition unit 23. Each of these units can be implemented by a processor running a program.

[0075] In one or more embodiments of the present application, the parsing unit 21 is configured to perform a set wavelet transform analysis based on the original carbon dioxide concentration time series to perform multi-level decomposition and decompose the original carbon dioxide concentration time series into multi-level approximation components and detail components.

[0076] In one or more embodiments of the present application, the reconstruction unit 22 is configured to reconstruct and generate an effective carbon dioxide concentration time series after decomposition.

[0077] In one or more embodiments of the present application, the identification unit 23 is configured to identify statistical features of the effective carbon dioxide concentration time series, and infer the scene type of the air-conditioned room based on the statistical features of the effective carbon dioxide concentration time series.

[0078] The original carbon dioxide concentration time series has frequency domain characteristics and time domain characteristics. The frequency domain characteristics refer to the distribution of the signal in the frequency domain, while the time domain characteristics refer to the change pattern of the signal on the time axis.

[0079] Frequency domain characteristics include periodic changes that occur at different time scales. On shorter time scales, such as within a single day, human activity, ventilation conditions, and changes in indoor and outdoor temperatures during the day and night can cause fluctuations in CO2 concentrations. During the day, there is more indoor and outdoor air exchange, resulting in lower CO2 concentrations. On a daily basis, real-time CO2 concentrations exhibit periodic changes. Time domain characteristics include trends that change over time.

[0080] The analysis unit 21 is configured to perform a wavelet transform analysis based on the original carbon dioxide concentration time series. Wavelet transform analysis is a signal processing tool that can determine the frequency characteristics of the original carbon dioxide concentration time series within a specific time period, or the signal characteristics within a time range at a specific frequency. Wavelet transform analysis is more suitable for processing non-stationary signals than traditional Fourier transform or other frequency domain methods. In the present invention, the trend of the original carbon dioxide concentration time series may be linear or nonlinear, or may show a repetitive pattern with periodic fluctuations. At the same time, the length of the cycle may be uncertain due to external factors, and may also be affected by external events to form a sudden change. It is a typical non-stationary signal, and wavelet transform analysis is more suitable for processing the original carbon dioxide concentration time series.

[0081] The analysis unit 21 uses a set wavelet transform to analyze the multi-level decomposition of the real-time carbon dioxide concentration, thereby making it easier to distinguish between noise characteristics and signal characteristics, thereby allowing for more flexible use of the separated noise and signal. The number of decomposition levels of the wavelet transform analysis can be adjusted. For example, if the original carbon dioxide concentration time series contains signals with low-frequency trends and high-frequency noise, a relatively small number of decomposition levels can be selected to improve the resolution of the low-frequency trends; if the original carbon dioxide concentration time series contains signals with characteristics in multiple frequency bands, a larger number of decomposition levels can be selected to better separate the characteristics of different frequency bands.

[0082] Generally speaking, measurement errors (such as sensor accuracy limitations and environmental noise), environmental influences (temperature, humidity, ventilation, etc.), and human activities (such as breathing, cooking, and smoking) can cause the raw carbon dioxide concentration time series to contain low-frequency trends and high-frequency noise signals. Periodic changes (such as the alternation of day and night and seasonal changes) and natural factors (such as plant photosynthesis) can cause the raw carbon dioxide concentration time series to contain signals with multi-band characteristics.

[0083] In one or more embodiments of the present application, the parsing unit 21 decomposes the original carbon dioxide concentration time series into multi-level approximate components and detail components; wherein the approximate components are effective signals, and the detail components are noise signals.

[0084] The wavelet transform analysis set in the present invention is introduced below.

[0085] The general form of the wavelet basis function in wavelet transform analysis is:

[0086]

[0087] Among them, a represents the scale factor, b represents the translation factor, It is the basic mother wavelet function, which can be used to construct a low-pass filter to extract the approximate component, that is, the low-frequency component in the real-time concentration of carbon dioxide. By varying the scale factor a, a series of mother wavelet functions of varying scales are generated. These functions are used to construct high-pass filters and extract detail components, or high-frequency components, from the real-time CO2 concentration, thereby enabling multi-scale decomposition and analysis of the real-time CO2 concentration. The translation factor b can localize the wavelet basis functions to characteristic locations in the real-time CO2 concentration, such as signal breakpoints and peaks. This helps capture important signal features within a specific timeframe.

[0088] In one or more embodiments of the present application, in a given wavelet transform analysis, a wavelet basis function is selected from the Db wavelet. The Db wavelet is a family of wavelet basis functions that have good compactness, orthogonality, and multi-resolution properties. The Db wavelet family generates wavelet basis functions of different orders by selecting different parameters, such as Db5, etc., which are not limited in this application.

[0089] Since the set wavelet transform analysis can adaptively adjust the decomposition scale according to the characteristics of the original carbon dioxide concentration time series, the analysis unit 21 can decompose the signal into components of different frequencies, and the signal characteristics in different frequency ranges can be better captured, so that the effective information and noise information can be effectively separated, and the essence of the real-time carbon dioxide concentration can be better understood.

[0090] The reconstruction unit 22 is configured to reconstruct and generate an effective carbon dioxide concentration time series after multi-level decomposition.

[0091] The effective carbon dioxide concentration time series can accurately reflect the characteristics of the original signal and better extract the characteristic information in the signal.

[0092] Based on the effective carbon dioxide concentration time series, the identification unit 23 can identify the statistical characteristics of the effective carbon dioxide concentration time series, and infer the scene type of the air-conditioned room according to the statistical characteristics of the effective carbon dioxide concentration time series.

[0093] For example, in office areas, carbon dioxide concentrations will increase significantly during office hours and remain at a relatively stable level, and will decrease after office hours. In classrooms, carbon dioxide concentrations will increase during class and decrease during breaks. By comparing these characteristics with the corresponding statistical characteristics of known scenarios, the scenario type of the air-conditioned room can be inferred, thereby providing a data basis for the monitoring and control of smart buildings.

[0094] The signal flow chart of the processing device 20 is as follows: Figure 7 shown.

[0095] This application combines wavelet transform analysis technology and statistical feature recognition technology to achieve accurate analysis and scene recognition of the carbon dioxide concentration time series in the air-conditioned room. By performing multi-level decomposition and reconstruction of the signal, noise and interference signals can be effectively removed and the signal quality can be improved. By performing statistical feature recognition on the effective carbon dioxide concentration time series, the scene type of the air-conditioned room can be accurately inferred, providing a reference basis for air conditioning. This application has the advantages of good real-time performance, high accuracy and intelligence.

[0096] like Figure 4 As shown, the processing device 20 further includes:

[0097] The estimation unit 24 is configured to estimate whether the statistical features of the valid carbon dioxide concentration time sequence match the preset scenario type estimation condition based on the statistical features within a determination period.

[0098] When matching the preset scenario type estimation condition based on the statistical features, the identification unit 23 identifies the valid carbon dioxide concentration time sequence as the corresponding scenario type, wherein the time length of the original carbon dioxide concentration time sequence includes one or more determination periods.

[0099] In one or more embodiments of the present application, the statistical features include the average value, the rate of change, the maximum value, and the minimum value. The preset scenario types include the classroom area, the office area, the catering place area, the medical place area, the residential public area, and the residential bedroom area. In one or more embodiments of the present application, the preset scenario types further include other areas, totaling 7 types.

[0100] In one or more embodiments of the present application, the preset scenario type estimation condition based on the statistical features includes the classroom area estimation condition, the office area estimation condition, the catering place area estimation condition, the medical place area estimation condition, the residential public area estimation condition, and the residential bedroom area estimation condition. When none of the above conditions is met, it is estimated as other areas. The above conditions are introduced one by one as follows.

[0101] For ease of description, represents the average value of the carbon dioxide real-time concentration at t0 to t1 in the original carbon dioxide concentration time sequence, represents the rate of change of the carbon dioxide real-time concentration at t0 to t1 in the original carbon dioxide concentration time sequence, T pmax represents the time at which the peak value of the carbon dioxide real-time concentration in the original carbon dioxide concentration time sequence appears, P max represents the maximum value of the carbon dioxide real-time concentration in the preset period in the original carbon dioxide concentration time sequence, P min represents the minimum value of the carbon dioxide real-time concentration in the preset period in the original carbon dioxide concentration time sequence.

[0102] The classroom area estimation condition includes:

[0103] wherein AM0 and AM1 are the time in the morning, for example, 07:30 and 11:30 respectively, and AM2 and AM3 are the time in the early morning, for example, 00:00 and 07:00 respectively, the meaning of the formula is that the average value of the carbon dioxide real-time concentration in the morning period is higher than the average value of the carbon dioxide real-time concentration in the early morning period, P1 is a constant, for example, it can be set to 200 ppm.

[0104] Among them, PM0 and PM1 are the afternoon times, for example, 13:00 and 16:30 respectively; PM2 and PM3 are the evening times, for example, 17:30 and 24:00 respectively. This formula means that the average value of the real-time concentration of carbon dioxide in the afternoon period is higher than the average value of the real-time concentration of carbon dioxide in the evening period.

[0105] AM4 and AM5 are the times in the morning, for example, 06:00 and 10:00 respectively. This formula means that the rate of change of the real-time concentration of carbon dioxide in the morning period is greater than zero, and the real-time concentration of carbon dioxide in the morning period increases.

[0106] Among them, PM4 and PM3 are the time in the evening, for example, 17:00 and 24:00 respectively. This formula means that the rate of change of the real-time carbon dioxide concentration in the evening period is less than zero, and the real-time carbon dioxide concentration in the evening period decreases.

[0107] T pmax ∈(AM6, PM6), where AM6 is the morning time, for example, 09:00, and PM6 is the evening time, for example, 21:00. This formula means the time period in which the peak of the real-time carbon dioxide concentration occurs in the original carbon dioxide concentration time series.

[0108] In real life, the activity times of people in office areas and classroom areas are relatively consistent. During the daytime on weekdays, the number of people is relatively large and the carbon dioxide concentration varies greatly; there is no one at night and the carbon dioxide concentration is lower; on weekends and holidays, there is usually no one indoors and the carbon dioxide concentration is low throughout the day. Therefore, in one or more embodiments of the present application, the office area inference conditions can be the same as the classroom area inference conditions, and can be further distinguished based on the data type label.

[0109] In one or more embodiments of the present application, a pre-processing unit is further included, which is used to assign a data type label to the carbon dioxide concentration detection signal of the air-conditioned room obtained by the carbon dioxide sensor 10, such as a season label, a monthly label, etc.

[0110] The following presumption conditions for distinction are added:

[0111] P max -P min ≤P2, assuming the preset period is 1 day, this means that the difference between the maximum and minimum real-time carbon dioxide concentrations within 1 day is higher than the preset difference. The preset difference P2 is a constant and can be set to 100 ppm.

[0112] P3 is a constant, which can be set as 700 ppm; AM2 is 00:00, and PM3 is 24:00.

[0113] Based on the feature of summer vacation, the classroom area and the office area are distinguished. The number of days in July and August that meet the above distinguishing presumption conditions is collected, and the number of days is divided by the total number of days. If the ratio of the two is higher than the set threshold, it is presumed to be a classroom area, and if the ratio of the two is lower than the set threshold, it is presumed to be an office area.

[0114] The restaurant area presumption condition includes:

[0115] Where PM7 and PM8 are afternoon times, for example, 12:00 and 14:00, respectively; AM5 is a morning time, for example, 10:00.

[0116] Where PM9, PM 10 and PM6 are afternoon times, for example, 15:00, 18:00 and 21:00, respectively.

[0117] Where AM9 is a morning time, and PM0 is an afternoon time, for example, 11:00 and 13:00, respectively.

[0118] Where PM4 and PM 13 are afternoon times, for example, 17:00 and 20:00, respectively.

[0119] T pmax ∈ (AM3, AM6)∪(PM7, PM8)∪(PM 11 , PM 12 ), where AM3 and AM6 are morning times, for example, 07:00 and 09:00, respectively, and PM7, PM8, PM 11 and PM 12 are afternoon times, for example, 12:00, 14:00, 19:00 and 22:00, respectively.

[0120] The features of the carbon dioxide concentration in the restaurant area include: the carbon dioxide concentration changes greatly before and after the meal time; and the carbon dioxide concentration is low at night when there is no one.

[0121] In one or more embodiments of the present application, in combination with the data type label assigned by the preprocessing unit, the following distinguishing presumption conditions can also be obtained:

[0122] If P 工作日max >P 节假日max , the restaurant area is presumed to be a canteen.

[0123] If P工作日max <P 节假日max , then the catering venue area is presumed to be a restaurant / hotel.

[0124] That is, during weekends and holidays, the carbon dioxide concentration in restaurants / hotels varies greatly, or during weekends and holidays, the carbon dioxide concentration in cafeterias remains stable and at a lower concentration level.

[0125] The presumptive conditions for medical facility areas include:

[0126] AM7 is the time in the morning, for example, 08:00; PM7, PM0 and PM1 are the time in the afternoon, for example, 12:00, 13:00 and 16:30 respectively; PM2 and PM3 are the time in the evening, for example, 17:30 and 24:00 respectively.

[0127] AM3 and AM9 are the morning times, for example, 07:00 and 11:00 respectively, and PM0 and PM4 are the afternoon times, for example, 13:00 and 17:00 respectively.

[0128] PM4 is the afternoon time, and PM3 is the evening time, for example, 17:00 and 24:00 respectively.

[0129] In one or more embodiments of the present application, combined with the data type label assigned by the preprocessing unit, the following distinction inference conditions can also be obtained:

[0130] P 工作日max >P 节假日max ;

[0131]

[0132] Data characteristics of medical facilities include: concentration changes more dramatically in the morning than in the afternoon, lower carbon dioxide concentrations at night, and more dramatic changes in carbon dioxide concentrations on weekends and during the heating period than on weekdays.

[0133] The presumptive conditions for residential common areas include:

[0134] Among them, PM 10 , PM6, PM0 and PM1 are the times in the afternoon, for example, 18:00, 21:00, 13:00, 16:30 respectively.

[0135] P max ≤P4, P4 is a constant and can be set to 1500ppm.

[0136] AM2 and AM10 The time in the morning is, for example, 00:00 and 05:00 respectively.

[0137] T pmax ∈(AM3,AM6)∪(PM 11 , PM 12 ), where AM3 and AM6 are the morning times, for example, 07:00 and 09:00 respectively, and PM 11 and PM 12 The times are evening, for example, 19:00 and 22:00 respectively.

[0138] Data characteristics of residential public areas include: CO2 concentration changes more dramatically in the morning before work / school hours and in the evening after school / get off work hours; and lower concentrations in the early morning.

[0139] The presumptive conditions for a residential bedroom area include:

[0140] AM2 and AM7 are morning times, for example, 00:00 and 08:00 respectively, and PM6 is afternoon time, for example, 21:00.

[0141] AM2 and AM 10 The time in the morning is, for example, 00:00 and 05:00 respectively.

[0142] T pmax ∈(AM2, AM3), where AM2 and AM3 are the times in the morning, for example, 00:00 and 07:00 respectively.

[0143] AM6 is the time in the morning, for example, 09:00, and PM7 is the time in the afternoon, for example, 12:00.

[0144] The following presumptions may also be added:

[0145] PM5 is the afternoon time, for example, 16:00, PM 13 It is the evening time, for example, 20:00.

[0146] The data characteristics of residential bedroom areas include: concentrations rise and remain at a high level in the early morning, and lower concentrations during the day.

[0147] The above are the scene type inference conditions that are preset based on experience and statistical characteristics.

[0148] In one or more embodiments of the present application, the preset scene type inference condition set based on statistical features is a classification model.

[0149] Specifically, the classification model is obtained through the following steps: First, a modeled CO2 concentration time series is collected from the air-conditioned room. The modeled CO2 concentration time series data can be collected in real time by the CO2 sensor 10, obtained from historical data records, or generated through simulation or data fusion. The modeled CO2 concentration time series are from different scene types. The modeled CO2 concentration time series are preprocessed, including removing outliers, filling missing values, and smoothing noise. Statistical features are extracted from the modeled CO2 concentration time series. The statistical features include one or more of the following: mean, rate of change, maximum, minimum, variance, autocorrelation coefficient, standard deviation, and coefficient of fluctuation. The modeled CO2 concentration time series are labeled, and each time series data is associated with its corresponding scene category to construct a labeled dataset. Based on the extracted statistical features and the labeled dataset, a classification model is trained using a machine learning algorithm. The machine learning algorithm can be a regression algorithm, decision tree, random forest, support vector machine, etc. During the training process, a cross-validation algorithm is used to evaluate the performance of the classification model, and parameters are adjusted to improve accuracy and generalization. The trained model is tested and evaluated using a test dataset. Evaluation metrics such as accuracy, precision, and F1 score can be selected. The trained model is deployed in the air conditioning device 1 , and the estimation unit 24 uses the classification model to estimate the scene type corresponding to the effective carbon dioxide concentration time series.

[0150] In one or more embodiments of the present application, the duration of the original carbon dioxide concentration time series includes multiple judgment cycles, for example, the duration of the original carbon dioxide concentration time series is M days, M is greater than or equal to 7; one week (7 days) is used as a judgment cycle to infer the scene type corresponding to the effective carbon dioxide concentration time series.

[0151] In one or more embodiments of the present application, Figure 5 As shown, the processing device 20 further includes a recording unit 25 , a reliability generating unit 26 and an output unit 27 . The recording unit 25 is configured to record the number of determination cycles estimated to be of the corresponding scene type.

[0152] The reliability generating unit 26 is configured to generate the reliability of the corresponding scene type based on the number of determination cycles, the duration of the determination cycle, and the duration of the original carbon dioxide concentration time series.

[0153] In one or more embodiments of the present application, it is assumed that the reliability of the scene type k is recorded as f k , then N k is the number of determination cycles estimated to correspond to the scene type, t is the determination cycle (e.g., 7 days), and M is the length of the original carbon dioxide concentration time series.

[0154] The reliability generation unit 26 generates the reliability of each corresponding scene type, which can be exemplarily recorded as f1, f2, f3, f4, f5, and f6, corresponding to the classroom area, office area, dining area, medical area, residential public area, and residential bedroom area, respectively.

[0155] The output unit 27 is configured to select a scene type that matches the reliability condition as the estimated scene based on the preset reliability estimation condition. The identification unit 23 estimates that the scene type selected by the output unit 27 and matching the reliability condition is the scene type of an air-conditioned room.

[0156] In one or more embodiments of the present application, the output unit 27 searches for the maximum value among the reliability of each corresponding scene type generated by the reliability generation unit 26, and when the maximum value is higher than the set threshold, selects the scene type corresponding to the maximum reliability value as the inferred scene to achieve the final judgment.

[0157] In one or more embodiments of the present application, the output unit 27 is further configured to pause outputting the inferred scene when multiple scene types matching the reliability condition are selected; and to use the selected scene type as the inferred scene when only one scene type matching the reliability condition is selected.

[0158] If two scenarios have the same reliability, the output of the inferred scenario will be suspended until the reliability is differentiated.

[0159] like Figure 6 As shown, in one or more embodiments of the present application, the processing device 20 further has an update unit 28, and the update unit 28 is configured to obtain the reliability of the corresponding scene type generated by the reliability generation unit 26 once within each preset update cycle; the output unit 27 is also configured to select the scene type that matches the reliability condition as the estimated scene based on the preset reliability inference condition according to the reliability of the corresponding scene type obtained by the update unit.

[0160] In one or more embodiments of the present application, the parsing unit 21 is configured to perform a set wavelet transform analysis based on the time series of the detection signal to perform a three-level decomposition, and in each level of decomposition, the approximate component of the previous level is further decomposed into an approximate component and a detail component. The approximate components of the third level and the detail components of each level are output to the prediction unit. As shown in the figure, in the first level decomposition, the detection signal is decomposed into an approximate component CA1 and a detail component CD1. In the second level decomposition, the approximate component CA1 is further decomposed into an approximate component CA2 and a detail component CD2. In the third level decomposition, the approximate component CA2 is further decomposed into an approximate component CA3 and a detail component CD3. After the three-level decomposition, the approximate component CA3 reflects the main characteristic parameters of the detection signal, such as periodicity and trend, the detail component CD1 represents the precision noise of the detection device, and the detail components CD2 and CD3 are interference noise acting on the detection device.

[0161] For example, Figure 8 is the time-frequency distribution diagram of the original carbon dioxide concentration time series, Figure 9 is the time-frequency distribution diagram of the approximate component signal CA1, Figure 10 is the time-frequency distribution diagram of the detail component signal CD1, Figure 11 is the time-frequency distribution diagram of the detail component signal CD2, Figure 12 is the video distribution diagram of the detail component signal CD3, Figures 8 to 12 The horizontal axis is the time axis, and the vertical axis is the scale axis. The energy of the signal is distributed in two dimensions: time and frequency.

[0162] In one or more embodiments of the present application, the reconstruction unit 22 is configured to generate an effective carbon dioxide concentration time series by weighted reconstruction after multi-level decomposition.

[0163] Specifically include Figure 13 Multiple steps shown:

[0164] Step S11: obtaining wavelet coefficients corresponding to the set wavelet transform analysis.

[0165] Step S12: assign a weight to each wavelet coefficient.

[0166] Step S13: multiply the wavelet coefficients by corresponding weights respectively, and add the weighted wavelet coefficients.

[0167] Step S14: reconstructing the sum of the weighted coefficients through inverse wavelet transform to generate an effective carbon dioxide time series.

[0168] After each level of wavelet transform analysis, wavelet coefficients are obtained, which are the projections of the signal on the wavelet basis functions and reflect the energy distribution of the signal in different frequency bands and time positions. When the three-level decomposition is performed as described above, four sets of wavelet coefficients are obtained, including three sets of detail coefficients (corresponding to CD1, CD2 and CD3) and one set of approximation coefficients (corresponding to CA3), denoted as A, B, C, D. Each wavelet coefficient is assigned a corresponding weight w1, w2, w3 and w4, and the wavelet coefficients are multiplied by the corresponding weights, and the weighted wavelet coefficients are added together, the sum of the weighted coefficients = w1*A + w2*B + w3*C + w4*D, and the sum of the weighted coefficients is reconstructed into the effective carbon dioxide concentration time series through inverse wavelet transform.

[0169] More specifically, in the wavelet decomposition process, a series of wavelet coefficients can be obtained by performing inner product operation between the original carbon dioxide concentration time series and the wavelet basis functions. These wavelet coefficients reflect the energy distribution characteristics of the original carbon dioxide concentration time series in different time positions and different scales. More specifically, the detail components are directly reconstructed from the wavelet coefficients of the same scale, reflecting the high-frequency detail information of the original carbon dioxide concentration time series at that scale; the approximation components are reconstructed from the wavelet coefficients of that scale and larger scales, reflecting the energy distribution of the signal at that scale and lower frequency bands. Since the wavelet coefficients reflect the energy distribution characteristics of the original carbon dioxide concentration time series in different time and frequency, by weighting and summing the wavelet coefficients, the weight of each time-frequency region can be accurately controlled, and the effective carbon dioxide concentration time series that meets the requirements can be flexibly reconstructed.

[0170] In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0171] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. Air conditioning equipment, including: a carbon dioxide sensor configured to obtain a real-time concentration of carbon dioxide in the air-conditioned room, record and generate a raw carbon dioxide concentration time series; It is characterized by further comprising: A processing device comprising: an analysis unit configured to perform a set wavelet transform analysis based on the original carbon dioxide concentration time series to perform multi-level decomposition, decomposing the original carbon dioxide concentration time series into multi-level approximate components and detail components; a reconstruction unit configured to reconstruct and generate an effective carbon dioxide concentration time series after multi-level decomposition; and An identification unit is configured to identify statistical features of the effective carbon dioxide concentration time series and infer the scene type of the air-conditioned room based on the statistical features of the effective carbon dioxide concentration time series.

2. The air conditioning equipment according to claim 1, characterized in that The processing device further includes: an estimating unit configured to estimate, within a determination period, whether the statistical characteristics of the effective carbon dioxide concentration time series match a preset scenario type estimating condition set based on the statistical characteristics; When matching a preset scene type estimation condition set based on statistical characteristics, the identification unit estimates that the effective carbon dioxide concentration time series is a corresponding scene type; wherein the duration of the original carbon dioxide concentration time series includes one or more of the determination periods.

3. The air conditioning equipment according to claim 2, characterized in that The duration of the original carbon dioxide concentration time series includes a plurality of the determination cycles; The processing device further includes: a recording unit configured to record the number of determination cycles estimated to be of the corresponding scene type; a reliability generating unit configured to generate a reliability corresponding to a scenario type based on the number of determination cycles, the duration of the determination cycles, and the duration of the original carbon dioxide concentration time series; and an output unit configured to select, based on a preset reliability estimation condition, a scenario type that matches the reliability condition; The recognition unit infers that the selected scene type that matches the reliability condition is the scene type of an air-conditioned room.

4. The air conditioning equipment according to claim 3, characterized in that The output unit is further configured to pause outputting the estimated scene when multiple scene types matching the reliability condition are selected; and to use the selected scene type as the estimated scene when only one scene type matching the reliability condition is selected.

5. The air conditioning equipment according to claim 4, characterized in that The processing device further includes: an updating unit configured to obtain the reliability of the corresponding scenario type generated by the reliability generating unit once within each preset updating period; The output unit is further configured to select, based on the reliability of the corresponding scene type obtained by the updating unit and based on a preset reliability estimation condition, a scene type that matches the reliability condition as the estimated scene.

6. The air conditioning equipment according to any one of claims 1 to 5, characterized in that: The parsing unit is configured to perform a set wavelet transform analysis based on the original carbon dioxide concentration time series to perform a three-level decomposition, wherein the first level decomposition decomposes the original carbon dioxide concentration time series into a first approximate component and a first detail component; the second level decomposition decomposes the first approximate component into a second approximate component and a second detail component; and the third level decomposition decomposes the second approximate component into a third approximate component and a third detail component.

7. The air conditioning equipment according to any one of claims 1 to 5, characterized in that: The reconstruction unit is configured to perform the following steps to weightedly reconstruct and generate an effective carbon dioxide concentration time series: Get the wavelet coefficients corresponding to the set wavelet transform analysis; assigning a weight to each of the wavelet coefficients; Multiplying the wavelet coefficients by corresponding weights respectively, and adding the weighted wavelet coefficients; The sum of the weighted coefficients is reconstructed through inverse wavelet transform to generate the effective carbon dioxide time series.

8. The air conditioning equipment according to any one of claims 1 to 5, characterized in that: The statistical characteristics include: one or more of: average value, rate of change, maximum value, minimum value, variance, autocorrelation coefficient, standard deviation, and fluctuation coefficient.

9. The air conditioning equipment according to any one of claims 1 to 5, characterized in that: Also includes: A pre-processing unit is used to assign a data type label to the carbon dioxide concentration detection signal of the air-conditioned room obtained by the carbon dioxide sensor.

10. The air conditioning equipment according to any one of claims 1 to 5, characterized in that: The scene types include: classroom areas, office areas, dining area areas, medical area areas, residential public areas and / or residential bedroom areas.

Images