Intelligent air volume control method and device for fresh air system

Abstract

The invention relates to the technical field of air volume adjustment, in particular to an intelligent air volume control method and device for a fresh air system, and the method comprises the steps that dimension data, collected at each moment in a current observation time period corresponding to a current to-be-adjusted moment, under each preset dimension are obtained; screening out a target abnormal dimension corresponding to each moment, and obtaining a target abnormal time period of each moment under each corresponding target abnormal dimension; determining the indoor air deterioration degree corresponding to each moment; clustering different moments in the current observation time period, and obtaining a target time period; according to all the target abnormal dimensions corresponding to different moments in all the target time periods and the indoor air deterioration degree, an overall air abnormal index corresponding to the current to-be-adjusted moment is determined; and adjusting and controlling the air volume of the fan at the current to-be-adjusted moment. Self-adaptive adjustment of the fan air volume of the fresh air system is achieved, and the reasonability of fan air volume control and adjustment is improved.

Description

Technical Field

[0001] This invention relates to the field of air volume regulation technology, specifically to an intelligent air volume control method and device for a fresh air system. Background Technology

[0002] A fresh air system is an indoor ventilation and air exchange device. The main fresh air unit is connected to an indoor air distributor via ducts. It mechanically and actively supplies fresh air into the room and exhausts it outdoors, forcing a "fresh air flow field" to form within the indoor space. It simultaneously expels stale indoor air and introduces fresh outdoor air into the room, continuously replenishing the living environment with filtered outdoor air. This allows people to breathe fresh, oxygen-rich, high-quality air indoors, thus meeting the need for indoor ventilation. Currently, the common method for controlling airflow is to operate the fan at a fixed airflow rate, thereby controlling the motor's air volume.

[0003] However, when the fans in a fresh air system operate at a fixed air volume to achieve air volume control, the following technical problems often arise: In reality, indoor air quality often varies at different times, and different indoor air qualities often require different air volumes. Therefore, setting the fan air volume to the same fixed air volume at different times may result in poor fan air volume control and adjustment, making it difficult to adaptively adjust indoor air quality. Summary of the Invention

[0004] To address the technical problem of poor rationality in the control and adjustment of fan air volume, this invention proposes an intelligent air volume control method and device for a fresh air system.

[0005] In a first aspect, the present invention provides an intelligent air volume control method for a fresh air system, the method comprising: Obtain the dimensional data of each preset dimension collected at each moment within the current observation period corresponding to the current moment to be adjusted; Based on the dimension data collected at different times under the same preset dimension, the target anomaly dimension corresponding to each time moment is selected from all preset dimensions, and the target anomaly time period under each target anomaly dimension corresponding to each time moment is obtained. Based on the dimensional data of the target anomaly period under the corresponding different target anomaly dimensions at each time point, determine the degree of indoor air deterioration at each time point; Based on the degree of indoor air deterioration at different times within the current observation period, clusters are formed at different times within the current observation period to obtain target clusters, and target time periods are obtained based on the continuous times within each target cluster. Based on all target anomaly dimensions and indoor air deterioration levels at different times within all target time periods, determine the overall air anomaly index corresponding to the current time to be adjusted; Based on the overall air quality anomaly index corresponding to the current time to be adjusted, the fan airflow is adjusted and controlled at the current time to be adjusted.

[0006] In conjunction with the first aspect above, in one possible implementation, the step of filtering out the target anomaly dimension corresponding to each time moment from all preset dimensions based on dimensional data collected at different times under the same preset dimension includes: Based on the dimension data of the same preset dimension collected at different times, determine the abnormal candidate time corresponding to each preset dimension; Filter out the target abnormal moment corresponding to each preset dimension from all candidate abnormal moments corresponding to each preset dimension; The preset dimension is defined as the target anomaly dimension corresponding to each target anomaly moment.

[0007] In conjunction with the first aspect above, in one possible implementation, determining the abnormal candidate time corresponding to each preset dimension based on dimensional data collected at different times under the same preset dimension includes: Any moment within the current observation period is designated as the marked moment, and the moment preceding the marked moment is designated as the reference moment. Any preset dimension is designated as the marked dimension. If the difference between the dimension data of the marked dimension collected at the marked time and the dimension data of the marked dimension collected at the reference time is greater than a preset difference threshold, then the marked time is determined as an abnormal candidate time corresponding to the marked dimension.

[0008] In conjunction with the first aspect above, in one possible implementation, the step of filtering out the target abnormal moment corresponding to each preset dimension from all candidate abnormal moments corresponding to that preset dimension includes: Any preset dimension is determined as the label dimension, and the continuous abnormal candidate moments corresponding to the label dimension constitute the abnormal candidate time period corresponding to the label dimension. Based on the duration of each abnormal candidate time period corresponding to the labeled dimension, and the maximum value and range of all dimension data under the labeled dimension collected within each abnormal candidate time period corresponding to the labeled dimension, the degree of sudden change in air quality corresponding to each abnormal candidate time period corresponding to the labeled dimension is determined. If the degree of air quality change in the abnormal candidate time period corresponding to the marked dimension is greater than the preset air quality change threshold, then each moment in the abnormal candidate time period is determined as the target abnormal moment corresponding to the marked dimension.

[0009] In conjunction with the first aspect above, in one possible implementation, obtaining the target anomaly time period for each moment under each corresponding target anomaly dimension includes: Any moment within the current observation period is designated as the marked moment, and any target anomaly dimension corresponding to the marked moment is designated as the marked anomaly dimension. The target abnormal times that are continuous with the marked time among all the target abnormal times corresponding to the marked abnormal dimension constitute the target abnormal time period under the marked abnormal dimension.

[0010] In conjunction with the first aspect above, in one possible implementation, determining the degree of indoor air deterioration at each moment based on the dimensional data of the target anomaly period under its corresponding different target anomaly dimensions includes: Any moment within the current observation period is designated as the marked moment. If the number of target anomaly dimensions corresponding to the marked moment is 0, then the indoor air deterioration degree corresponding to the marked moment is set to a constant of 0. If the number of target anomaly dimensions corresponding to the marked time is 1, then the indoor air deterioration degree corresponding to the marked time is set to a constant of 0.1; If the number of target anomaly dimensions corresponding to the marked time is greater than 1, then based on the correlation between the dimensional data of the marked time in the target anomaly time period under different target anomaly dimensions, the degree of change of the marked time under each target anomaly dimension is determined. Based on the degree of change of the marked time under different target anomaly dimensions, the degree of sudden change in air quality corresponding to the anomaly candidate time period to which the marked time belongs among all anomaly candidate time periods corresponding to different target anomaly dimensions, and the number of target anomaly dimensions corresponding to the marked time, the degree of indoor air deterioration corresponding to the marked time is determined.

[0011] In conjunction with the first aspect above, in one possible implementation, determining the degree of influence of the change of the marked time in each corresponding target anomaly dimension based on the correlation between the dimensional data of the marked time within the target anomaly time period under its corresponding different target anomaly dimensions includes: The initial abnormal data sequence for each target abnormal time period under each target abnormal dimension of the marked time is formed by taking all the dimension data of the target abnormal time under each target abnormal dimension of the marked time. Interpolation processing is performed on the initial abnormal data sequences of the marked time under different target abnormality dimensions to obtain the target abnormal data sequences of the marked time under different target abnormality dimensions, wherein the number of elements in the different target abnormality data sequences is the same; The degree of simultaneous change between each pair of target anomaly dimensions at the marked time is determined based on the number of elements in the initial anomaly data sequence at each pair of target anomaly dimensions at the marked time, and the Pearson correlation coefficient between the target anomaly data sequences at each pair of target anomaly dimensions at the marked time. The mean of the degree of simultaneous change of the marked time in each of its corresponding target anomaly dimensions and all other target anomaly dimensions is determined as the degree of influence of the change of the marked time in each of its corresponding target anomaly dimensions.

[0012] In conjunction with the first aspect above, in one possible implementation, determining the overall air anomaly index corresponding to the current time to be adjusted, based on all target anomaly dimensions and indoor air deterioration levels at different times within all target time periods, includes: All target anomaly dimensions corresponding to each time moment constitute the target anomaly dimension set corresponding to each time moment; Based on the intersection of the target anomaly dimension sets corresponding to different times within each target time period, each target time period is divided into sub-time periods. Based on the duration of different sub-periods within each target period and the number of elements in the intersection of the target anomaly dimension sets corresponding to all times within each sub-period of each target period, the complex air anomaly index corresponding to each target period is determined. Based on the complex air quality indicators corresponding to each target time period and the average indoor air quality deterioration at all times within each target time period, the air quality indicators corresponding to each target time period are determined. Select the period with the lowest corresponding air quality index from all target periods and use it as a reference period; If the air quality index corresponding to the target time period is less than or equal to the preset quality threshold, then the target time period will be determined as a period with poor air quality. Based on the cumulative value of the durations corresponding to all periods with poor air quality, the air quality index corresponding to the reference period, and the duration between the end time of the reference period and the current time to be adjusted, the overall air quality anomaly index corresponding to the current time to be adjusted is determined.

[0013] In conjunction with the first aspect above, in one possible implementation, the step of segmenting each target time period to obtain sub-time periods based on the intersection of the target anomaly dimension sets corresponding to different times within each target time period includes: If the intersection between the target anomaly dimension sets corresponding to two adjacent time points is empty, then the later of these two time points is determined as the temporary time point; Each target time period is divided into sub-time periods by using temporary moments within each target time period as dividing points.

[0014] Secondly, the present invention provides an intelligent airflow control device for a fresh air system, comprising a processor and a memory, wherein the processor is configured to process instructions stored in the memory to implement the method described in the first aspect or any possible implementation thereof. Specifically, the device comprises: The dimension data acquisition module is used to acquire dimension data for each preset dimension collected at each moment within the current observation period corresponding to the current moment to be adjusted. The filtering and acquisition module is used to filter out the target abnormal dimension corresponding to each time moment from all preset dimensions based on the dimension data collected at different times under the same preset dimension, and to acquire the target abnormal time period under each target abnormal dimension at each time moment. The indoor air deterioration degree determination module is used to determine the indoor air deterioration degree at each time point based on the dimensional data of the target anomaly period under the corresponding different target anomaly dimensions at each time point. The clustering and acquisition module is used to cluster different moments within the current observation period according to the degree of indoor air deterioration at different times, obtain target clusters, and acquire target time periods based on the continuous moments within each target cluster. The overall air anomaly index determination module is used to determine the overall air anomaly index corresponding to the current time to be adjusted based on all target anomaly dimensions and indoor air deterioration levels at different times within all target time periods. The air volume regulation and control module is used to regulate and control the fan air volume at the current time of adjustment based on the overall air anomaly index corresponding to the current time of adjustment.

[0015] Thirdly, a server is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to perform the methods of the first aspect or any possible implementation thereof.

[0016] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0017] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0018] The present invention has the following beneficial effects: This invention provides an intelligent airflow control method for a fresh air system, which achieves adaptive adjustment of the fan airflow of the fresh air system, solves the technical problem of poor rationality in fan airflow control adjustment, and improves the rationality of fan airflow control adjustment. Specifically, this invention analyzes dimensional data under different preset dimensions within the current observation period, quantifies multiple indicators related to the current indoor environmental conditions, such as the degree of indoor air deterioration and overall air anomaly indicators, thereby realizing the adjustment and control of the fan airflow at the current time to be adjusted, and improving the rationality of the fan airflow control adjustment of the fresh air system. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of an intelligent air volume control method for a fresh air system according to the present invention; Figure 2 This is a schematic diagram of the composition structure of an intelligent air volume control device for a fresh air system according to the present invention; Figure 3 This is a schematic diagram of the structure of a computer device according to the present invention. Detailed Implementation

[0021] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the technical solution proposed according to the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] refer to Figure 1The flowchart illustrates some embodiments of an intelligent airflow control method for a fresh air system according to the present invention. The intelligent airflow control method for the fresh air system includes the following steps: Step S1: Obtain the dimensional data of each preset dimension collected at each moment within the current observation period corresponding to the current moment to be adjusted.

[0024] The "current time to be adjusted" refers to the moment when airflow adjustment is scheduled. The "current observation period" is a pre-set time period ending at the current time to be adjusted, used to observe changes in the indoor environment and assist in airflow adjustment at that time. The current observation period can be 1 hour. The "preset dimensions" are pre-set dimensions affecting indoor environmental quality. The number of preset dimensions is pre-set, up to 5. For example, preset dimensions can be, but are not limited to: carbon dioxide concentration, carbon monoxide concentration, formaldehyde concentration, PM2.5 concentration, and ozone concentration. The dimension data under each preset dimension can be the normalized value of that preset dimension. For example, the dimension data under the carbon dioxide concentration dimension can be the normalized value of the indoor carbon dioxide concentration.

[0025] As an example, taking carbon dioxide concentration as an example, the method to obtain the dimensional data of carbon dioxide concentration at each moment in the current observation period corresponding to the current time to be adjusted can be as follows: In the current observation period, the indoor carbon dioxide concentration is collected once every 1 second through the carbon dioxide concentration sensor, and the normalized value of the indoor carbon dioxide concentration collected each time is recorded as the dimensional data of carbon dioxide concentration.

[0026] Step S2: Based on the dimension data collected at different times under the same preset dimension, filter out the target anomaly dimension corresponding to each time from all preset dimensions, and obtain the target anomaly time period under each target anomaly dimension corresponding to each time.

[0027] As an example, this step may include the following steps: The first step, based on dimensional data collected at different times under the same preset dimension, is to determine the candidate time of anomalies for each preset dimension. This may include the following steps: The first sub-step involves determining any moment within the current observation period as the marked moment, determining the moment preceding the marked moment as the reference moment, and determining any preset dimension as the marked dimension.

[0028] The second sub-step is as follows: if the difference between the dimension data of the marked dimension collected at the marked time and the dimension data of the marked dimension collected at the reference time is greater than a preset difference threshold, then the marked time is determined as an abnormal candidate time corresponding to the marked dimension.

[0029] The preset difference threshold can be a pre-set threshold, which can be 0.3.

[0030] It should be noted that, under normal circumstances, changes in various aspects of indoor environmental data tend to be relatively slow. If the data suddenly shows significant abnormal changes (i.e., the absolute value of the difference is very large), it may indicate that some activities are taking place indoors, such as cooking or gatherings of many people, leading to a sharp increase in indoor carbon dioxide and cooking fumes. In this case, it is often necessary to increase the airflow and introduce fresh air in a timely manner to ensure air quality.

[0031] The second step, selecting the target anomaly moment corresponding to each preset dimension from all candidate anomalies for that preset dimension, may include the following sub-steps: The first sub-step involves determining any preset dimension as the label dimension, and constructing the continuous abnormal candidate times corresponding to the label dimension into the abnormal candidate time periods corresponding to the label dimension.

[0032] For example, if there are 11 candidate times for anomalies corresponding to the labeled dimension, and these 11 candidate times are 9:05:01, 9:05:02, 9:05:03, 9:05:04, 9:08:06, 9:08:07, 9:08:08, 9:27:20, 9:27:21, 9:27:22, and 9:27:23, and the duration between adjacent data collection times is 1 second, then there can be 3 candidate time periods for anomalies corresponding to the labeled dimension. These 3 candidate time periods can be: the time period starting at 9:05:01 and ending at 9:05:04, the time period starting at 9:08:06 and ending at 9:08:08, and the time period starting at 9:27:20 and ending at 9:27:23.

[0033] The second sub-step involves determining the degree of sudden change in air quality for each abnormal candidate time period corresponding to the aforementioned labeled dimension, based on the duration of each abnormal candidate time period corresponding to the aforementioned labeled dimension, and the maximum value and range of all dimension data collected within each abnormal candidate time period corresponding to the aforementioned labeled dimension.

[0034] For example, if any abnormal candidate time period corresponding to the labeled dimension is determined as a labeled candidate time period, the formula for determining the degree of sudden change in air quality corresponding to the labeled candidate time period can be: ; Where b represents the degree of sudden change in air quality corresponding to the candidate time period. This is the normalization function. t is the duration corresponding to the candidate labeling period, which is equal to the duration between the start and end times of the candidate labeling period. c is the maximum value among all dimension data collected within the candidate labeling period under the labeled dimension. L is the range of all dimension data collected within the candidate labeling period under the labeled dimension.

[0035] It should be noted that a larger t usually indicates more anomalous candidate moments within the labeled candidate time period, and thus more likely abnormal data in the labeled dimension. A larger c usually indicates a greater likelihood of anomalies occurring within the labeled candidate time period. A larger L usually indicates greater fluctuations in the labeled dimension data within the labeled candidate time period, and a higher probability of anomalies. Therefore, a larger b usually indicates that the labeled dimension is more likely to cause a deterioration in indoor environmental quality within the labeled candidate time period.

[0036] The third sub-step is to determine each moment within the abnormal candidate time period corresponding to the above-mentioned marked dimension as the target abnormal moment corresponding to the above-mentioned marked dimension if the degree of air quality change is greater than the preset quality change threshold.

[0037] The preset quality change threshold can be a pre-set threshold, which can be 0.7.

[0038] The third step is to define the preset dimension as the target anomaly dimension corresponding to each target anomaly moment.

[0039] Among them, the target anomaly dimension corresponding to the target anomaly time often represents the dimension in which the target anomaly occurs at that target anomaly time.

[0040] For example, if the target anomaly time corresponding to the carbon dioxide concentration dimension is 9:08:06, then the carbon dioxide concentration dimension can be a target anomaly dimension corresponding to 9:08:06.

[0041] It should be noted that the same preset dimension may correspond to multiple different target anomaly times, and the same time may correspond to multiple target anomaly dimensions.

[0042] The fourth step is to determine any point in the current observation period as the marked point, and to determine any target anomaly dimension corresponding to the marked point as the marked anomaly dimension.

[0043] The fifth step is to construct the target abnormal time period of the marked time under the marked abnormal dimension from all the target abnormal times corresponding to the marked abnormal dimension.

[0044] For example, if there are 7 target abnormal times corresponding to the marked abnormal dimension, and these 7 target abnormal times are 9:10:02, 9:10:03, 9:10:04, 9:10:05, 9:10:06, 9:20:08, and 9:20:09, and the marked time is 9:10:04, then the target abnormal time period under the marked abnormal dimension can be the time period starting from 9:10:02 and ending at 9:10:06.

[0045] Step S3: Determine the degree of indoor air deterioration at each time point based on the dimensional data of the target anomaly period under the corresponding different target anomaly dimensions.

[0046] It should be noted that, in reality, the more target anomaly dimensions there are at the same time, the more dimensional data anomalies occur at that time. This often indicates a greater likelihood of dimensional features affecting the indoor environment at that time, and consequently, a higher probability of poor air quality. Furthermore, a typical characteristic of indoor environmental quality is the correlation and synergistic deterioration of multiple factors. Therefore, the more target anomaly dimensions there are at the same time, and the higher the correlation between these anomaly dimensions, the more likely it is to cause air quality deterioration at that time.

[0047] As an example, this step may include the following steps: The first step is to designate any point in the current observation period as the marked point. If the number of target anomaly dimensions corresponding to the marked point is 0, then the indoor air deterioration level corresponding to the marked point is set to a constant of 0.

[0048] The second step is to set the indoor air deterioration level corresponding to the above-mentioned marked time to a constant of 0.1 if the number of target anomaly dimensions corresponding to the above-mentioned marked time is 1.

[0049] The third step, if the number of target anomaly dimensions corresponding to the above-mentioned marked time is greater than 1, then determining the degree of indoor air deterioration corresponding to the above-mentioned marked time based on the dimensional data of the target anomaly time period under the different target anomaly dimensions corresponding to the above-mentioned marked time may include the following sub-steps: The first sub-step, determining the degree of influence of changes in each target anomaly dimension of the marked time based on the correlation between the dimensional data within the target anomaly time period under the different target anomaly dimensions corresponding to the marked time, may include the following steps: First, the data of all dimensions within the target anomaly period under each target anomaly dimension at the marked time are used to form the initial anomaly data sequence under each target anomaly dimension at the marked time.

[0050] The initial abnormal data sequence can be a time series.

[0051] Next, the initial abnormal data sequences at the marked times under different target abnormality dimensions are interpolated using a polynomial interpolation algorithm to obtain the target abnormal data sequences at the marked times under different target abnormality dimensions.

[0052] The number of elements in different target anomaly data sequences can be the same. The target anomaly data sequence can be the initial anomaly data sequence after interpolation.

[0053] It should be noted that the interpolation processing of the initial anomaly data sequences at the marked time under different target anomaly dimensions is mainly to interpolate the number of elements in different initial anomaly data sequences to be consistent, which is mainly to facilitate the subsequent calculation of the correlation between different initial anomaly data sequences.

[0054] Then, based on the number of elements in the initial anomalous data sequence at each of the two target anomalous dimensions corresponding to the above-mentioned marked time, and the Pearson correlation coefficient between the target anomalous data sequences at each of the two target anomalous dimensions corresponding to the above-mentioned marked time, the degree of simultaneous change between each of the two target anomalous dimensions corresponding to the above-mentioned marked time is determined.

[0055] Among them, the Pearson correlation coefficient between different target anomalous data sequences can characterize the correlation between different initial anomalous data sequences.

[0056] For example, the formula for determining the degree of simultaneous change of a marker time across its corresponding different target anomaly dimensions can be: ; ; ; in, It represents the degree of simultaneous change between the i-th and j-th target anomaly dimensions at the marked time. i and j are the indices of the different target anomaly dimensions corresponding to the marked time. It is a normalization function. It is the minimum number of initial abnormal data between the i-th and j-th target abnormal dimensions at the marked time. It is an exponential function with the natural constant as its base. It is the maximum number of initial abnormal data between the i-th and j-th target abnormal dimensions at the marked time. It is the Pearson correlation coefficient between the target anomaly data sequence at the marked time and the target anomaly data sequence at the corresponding i-th target anomaly dimension and the target anomaly data sequence at the j-th target anomaly dimension. It is a function that takes the minimum value. It is a function that takes the maximum value. It is the number of elements in the initial anomaly data sequence at the marked time in the corresponding i-th target anomaly dimension. It is the number of elements in the initial anomaly data sequence at the marked time in the corresponding j-th target anomaly dimension.

[0057] It should be noted that when A larger value generally indicates a larger minimum number of elements in the initial anomalous data sequence at the marked time in the corresponding i-th and j-th target anomaly dimensions. This also generally indicates that the i-th and j-th target anomaly dimensions originally had more elements involved in the Pearson correlation coefficient calculation, and that the calculation... The more reliable it is, the better. When A larger value usually indicates that the interpolation algorithm supplements more data, and thus the computation is more efficient. The more unreliable it is, the less trustworthy it becomes. A larger value generally indicates a greater likelihood of correlation between the i-th and j-th target anomaly dimensions at the labeling time, and a greater likelihood of co-deterioration between them. Therefore, when... The larger the value, the more likely the i-th and j-th target anomaly dimensions are to co-deteriorate at the marked time.

[0058] Finally, the mean of the degree of simultaneous change of the above-mentioned marked time in each of its corresponding target anomaly dimensions and all other target anomaly dimensions is determined as the degree of influence of the change of the above-mentioned marked time in each of its corresponding target anomaly dimensions.

[0059] For example, the formula for determining the degree of influence of changes at a given time point under its corresponding different target anomaly dimensions can be: ; in, This represents the degree of influence of changes at the marked time on the corresponding i-th target anomaly dimension. i and j are the indices of the different target anomaly dimensions corresponding to the marked time. N is the number of target anomaly dimensions corresponding to the marked time. It represents the degree of simultaneous change between the i-th and j-th target anomaly dimensions at the marked time.

[0060] It should be noted that when The larger the value, the more likely there is a certain correlation between the i-th target anomaly dimension and other target anomaly dimensions at the labeling time, and the more likely there is a cooperative deterioration between the i-th target anomaly dimension and other target anomaly dimensions at the labeling time.

[0061] The second sub-step, based on the degree of influence of the changes at the marked time under its corresponding different target anomaly dimensions, the degree of sudden change in air quality corresponding to the anomaly candidate time period to which the marked time belongs among all anomaly candidate time periods corresponding to the different target anomaly dimensions corresponding to the marked time, and the number of target anomaly dimensions corresponding to the marked time, determines the formula corresponding to the degree of indoor air deterioration at the marked time as follows: ; Where E is the degree of indoor air deterioration at the marked time, and its value range can be [0.2, 1]. This is the normalization function. N is the number of target anomaly dimensions corresponding to the marked time. n is the preset number of dimensions. i is the index of the target anomaly dimension corresponding to the marked time. It represents the degree of influence of changes at the marked time in the corresponding i-th target anomaly dimension. It represents the degree of sudden change in air quality corresponding to the anomaly candidate time period to which the marked time belongs, among all anomaly candidate time periods corresponding to the i-th target anomaly dimension.

[0062] It should be noted that when A larger value usually indicates that there may be more types of environmental dimensions exhibiting anomalies at the marked time. A larger value generally indicates that the i-th target anomaly dimension is more likely to cause a deterioration in indoor environmental quality at the marked time. A larger value for E generally indicates a greater likelihood of correlation between the i-th target anomaly dimension and other target anomaly dimensions at the marked time, and a greater likelihood of synergistic deterioration between the i-th target anomaly dimension and other target anomaly dimensions at the marked time. Therefore, E can characterize the degree of indoor air deterioration at the marked time. A larger value generally indicates a relatively poor indoor air quality at the marked time, and a greater need for indoor air conditioning.

[0063] Step S4: Based on the degree of indoor air deterioration at different times within the current observation period, cluster the different times within the current observation period to obtain target clusters, and obtain target time periods based on the continuous times within each target cluster.

[0064] It should be noted that in reality, indoor environmental anomalies often exhibit "continuous scene characteristics" (such as during dinner cooking time), and the overall anomaly level at a single moment may fluctuate slightly due to instantaneous disturbances (such as a sudden door opening). Adjusting the airflow individually based on the overall anomaly level at each moment would often lead to frequent changes in fresh air volume, increasing equipment wear and tear and potentially affecting indoor comfort due to sudden airflow changes. Therefore, this embodiment of the invention adjusts the airflow by analyzing the overall environmental changes within the current observation period. The previous airflow adjustment time before the current time to be adjusted can be the time before the current observation period.

[0065] The target time period can represent a period of continuous abnormality, a period of transient disturbance abnormality, or a normal period.

[0066] As an example, this step may include the following steps: The first step is to cluster the different times within the current observation period according to the degree of indoor air deterioration at different times, thus obtaining the target cluster.

[0067] For example, based on the degree of indoor air deterioration at different times within the current observation period, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster different times within the current observation period, and each cluster obtained at this time is recorded as the target cluster.

[0068] The second step is to obtain the target time period based on the continuous time within each target cluster.

[0069] For example, if there are 11 times within a target cluster, namely 9:11:01, 9:11:02, 9:11:03, 9:11:04, 9:18:06, 9:18:07, 9:18:08, 9:40:02, 9:40:02, 9:40:02, and 9:40:023, and the duration between adjacent data acquisition times is 1 second, then 3 target time periods can be obtained. These 3 target time periods can be: the time period starting at 9:11:01 and ending at 9:11:04; the time period starting at 9:18:06 and ending at 9:18:08; and the time period starting at 9:40:020 and ending at 9:40:023.

[0070] Step S5: Determine the overall air anomaly index corresponding to the current time to be adjusted based on all target anomaly dimensions and indoor air deterioration levels at different times within all target time periods.

[0071] It's important to note that in reality, poor indoor air quality can be caused by multiple factors. For example, at certain times, cooking might cause anomalies in environmental data such as temperature and humidity, while at other times, gatherings or renovations could lead to increased carbon dioxide and formaldehyde levels. If the types of anomalous data remain stable within each target time period, it indicates that the cause of poor air quality is relatively singular, affecting fewer types of environmental data and having a smaller impact on air quality. Conversely, if the types of anomalous data change continuously, it suggests that the cause of poor air quality is more complex and likely more diverse, with a greater impact on air quality. In such cases, increased airflow adjustment is more necessary.

[0072] As an example, this step may include the following steps: The first step is to construct a set of target anomaly dimensions for each time step, which includes all target anomaly dimensions at each time step.

[0073] The second step involves segmenting each target time period based on the intersection of the target anomaly dimension sets corresponding to different times within that time period. This segmentation can include the following sub-steps: The first sub-step is to determine the later of the two time points as the temporary time point if the intersection between the target anomaly dimension sets corresponding to two adjacent time points is empty.

[0074] The second sub-step involves dividing each target time period into sub-time periods by using temporary moments within each target time period as dividing points.

[0075] It should be noted that the data dimension types that exhibit anomalies within a sub-period are relatively stable.

[0076] The third step is to determine the complex air anomaly index for each target time period based on the duration of different sub-time periods within each target time period and the number of elements in the intersection of the target anomaly dimension sets corresponding to all times within each sub-time period within each target time period.

[0077] For example, the formula for determining the complex air anomaly indicators corresponding to the target time period can be: ; in, This is the complex air quality index corresponding to the m-th target time period. m is the sequence number of the target time period. It is an exponential function with the natural constant as its base. is the number of sub-time periods within the m-th target time period. 'a' is the sequence number of the sub-time periods within the m-th target time period. It is the duration of the a-th sub-period within the m-th target time period. It is the number of elements in the intersection of the target anomaly dimension sets corresponding to all times within the m-th target time period and the a-th sub-time period. It is the number of elements in the union of the target anomaly dimension sets corresponding to all times within the m-th target time period and the a-th sub-time period.

[0078] It should be noted that when The smaller the value, the shorter the sub-period length within the m-th target time period; the shorter the duration of the same anomalous dimension within the m-th target time period; the more likely the dimensional type of the anomalous data within the m-th target time period is to change continuously; and the more likely the causes of the anomalies within the m-th target time period are to be diverse. A larger value often indicates that the dimensions exhibiting anomalies at different times within the a-th sub-period are more likely to be the same, and that the data dimension types exhibiting anomalies within the a-th sub-period are relatively more stable. Conversely, when... The smaller the value, the more unstable the data dimension type tends to be within the a-th sub-period, and the more complex the reasons for poor air quality within that sub-period. Therefore, when The larger the value, the more unstable the data dimension type is in the m-th target time period, and the more complex the reasons for the poor air quality in the m-th target time period are.

[0079] The fourth step is to determine the air quality index for each target time period based on the air anomaly complexity index corresponding to each target time period and the average indoor air deterioration level at all times within each target time period.

[0080] For example, the formula for determining the air quality index corresponding to the target time period can be: ; in, This is the air quality index corresponding to the m-th target time period. m is the sequence number of the target time period. It is an exponential function with the natural constant as its base. It is the complex air quality indicator corresponding to the m-th target time period. It is the average of the indoor air deterioration level at all times within the m-th target time period.

[0081] It should be noted that, This value can characterize the degree of indoor air deterioration during the m-th target time period. A larger value generally indicates poorer indoor air quality during the m-th target time period, and thus requires a larger airflow for indoor air conditioning. A larger value often indicates that the data dimension type causing the anomalies in the m-th target time period is relatively unstable, and the reasons for the poor air quality in the m-th target time period are often more complex. Therefore, when A larger value usually indicates that the indoor air quality is relatively better during the m-th target time period.

[0082] The fifth step is to select the target time period with the lowest corresponding air quality index from all target time periods as the reference time period.

[0083] Step 6: If the air quality index corresponding to the target time period is less than or equal to the preset quality threshold, then the target time period is determined as a period with poor air quality.

[0084] The preset quality threshold can be a pre-set threshold, which can be 0.7.

[0085] Step 7: Based on the cumulative value of the durations corresponding to all periods with poor air quality, the air quality index corresponding to the above reference periods, and the duration between the end time of the above reference periods and the current time to be adjusted, determine the overall air quality anomaly index corresponding to the current time to be adjusted.

[0086] For example, the formula for determining the overall air quality anomaly index corresponding to the current time to be adjusted can be: ; Where Q is the overall air anomaly index corresponding to the current time to be adjusted. It is the sum of the durations corresponding to all periods with poor quality. It is the duration corresponding to the current observation period. It is an exponential function with the natural constant as its base. p is the air quality index corresponding to the reference period. k is the duration between the end of the reference period and the current time to be adjusted.

[0087] It should be noted that in reality, changes in indoor air quality are often delayed and can be affected by sudden events (such as sudden changes in pedestrian traffic or indoor activities). Therefore, when adjusting airflow for the current time period, relying solely on air quality indicators within a specific timeframe may not reflect the actual current air quality. It is also necessary to consider the air quality of several historical periods with poor air quality and their potential impact on future air quality to improve the accuracy of system airflow adjustment and maintain a stable and comfortable indoor environment. A smaller p generally indicates a relatively worse indoor air quality within the reference period, suggesting a higher likelihood of periods of poor indoor air quality within the current observation period. A smaller k generally indicates that periods of poor indoor air quality within the current observation period are closer to the current time period, and that the impact of periods of poor indoor air quality on the current time period is greater. The smaller the value of Q, the shorter the total duration of periods with poor air quality within the current observation period. This usually indicates that the air quality has remained stable at a good level for a long period, thus requiring less airflow. Therefore, a larger Q value usually indicates poorer indoor environmental quality within the current observation period, and thus requires more airflow at the moment of adjustment.

[0088] Step S6: Adjust and control the fan air volume at the current time of adjustment based on the overall air anomaly index corresponding to the current time of adjustment.

[0089] As an example, this step may include the following steps: The first step is to determine the fan airflow correction value for the current time to be adjusted based on the overall air quality anomaly index.

[0090] For example, the formula for determining the fan airflow correction value corresponding to the current adjustment time can be: ; Where f is the fan air volume correction value corresponding to the current time to be adjusted. It is the minimum non-zero air volume that the fan can achieve during operation, representing the lower limit of the fan's safe and stable operation. It is a normalization function. Q is the overall air anomaly index corresponding to the current time to be adjusted. It is the maximum air volume that the fan can achieve during operation, representing the upper limit of the fan's capacity.

[0091] It should be noted that a larger Q value often indicates a poorer indoor environmental quality during the current observation period, and consequently, a greater demand for airflow at the current adjustment time. Therefore, f can represent the required fan airflow at the current adjustment time.

[0092] The second step is to use a PID (Proportional Integral Derivative) controller to adjust the fan airflow at the current time to be adjusted to its corresponding fan airflow correction value.

[0093] It should be noted that the current fan airflow correction value at the moment of adjustment can be input into the PID controller, which outputs a control signal. This control signal will be used to adjust the fan speed or airflow. The fan will then adjust its airflow in real time according to the signal output by the PID controller to maintain indoor air quality within the required range.

[0094] Among them, PID control is a common feedback control algorithm that adjusts the air volume by monitoring air quality data (such as carbon dioxide concentration, PM2.5, etc.) in real time to maintain indoor air quality within the set required range.

[0095] Each environmental dimension has its unique fluctuation patterns and influencing factors. Simply analyzing anomalies in one dimension may lead to an overly simplistic system response. This invention enhances the system's intelligence by combining data from multiple dimensions, helping it to understand environmental changes more comprehensively. Through intersection analysis, the system can make more rational control decisions based on the relationships between different data points, improving the accuracy and responsiveness of the intelligent airflow adjustment of the fresh air system.

[0096] refer to Figure 2 Based on the same inventive concept as the above-described method embodiments, this invention provides an intelligent airflow control device for a fresh air system. The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of an intelligent airflow control method for a fresh air system, specifically including: The dimension data acquisition module 201 is used to acquire dimension data of each preset dimension collected at each moment within the current observation time period corresponding to the current moment to be adjusted. The filtering and acquisition module 202 is used to filter out the target abnormal dimension corresponding to each time moment from all preset dimensions based on the dimension data of the same preset dimension collected at different times, and to acquire the target abnormal time period of each time moment under each target abnormal dimension. The indoor air deterioration degree determination module 203 is used to determine the indoor air deterioration degree at each time point based on the dimensional data of the target anomaly period under the corresponding different target anomaly dimensions at each time point. The clustering and acquisition module 204 is used to cluster different moments in the current observation period according to the degree of indoor air deterioration at different times in the current observation period, obtain target clusters, and acquire target time periods based on the continuous moments in each target cluster. The overall air anomaly index determination module 205 is used to determine the overall air anomaly index corresponding to the current time to be adjusted based on all target anomaly dimensions and indoor air deterioration degree corresponding to different times within all target time periods. The air volume regulation and control module 206 is used to regulate and control the fan air volume at the current time of adjustment based on the overall air anomaly index corresponding to the current time of adjustment.

[0097] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can execute any of the aforementioned intelligent air volume control methods for fresh air systems.

[0098] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to execute any of the above-described intelligent airflow control methods for a fresh air system.

[0099] Based on the same inventive concept as the above-described method embodiments, the present invention provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to execute any of the above-described intelligent airflow control methods for a fresh air system.

[0100] Based on the same inventive concept as the above-described method embodiments, the present invention provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any of the above-described intelligent airflow control methods for fresh air systems.

[0101] In summary, this invention quantifies multiple indicators related to the current indoor environment by analyzing dimensional data under different preset dimensions within the current observation period, such as the degree of indoor air deterioration and overall air abnormality indicators. This enables the adjustment and control of the fan air volume at the current time to be adjusted, and improves the rationality of the fan air volume control and adjustment of the fresh air system.

[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent airflow control in a fresh air system, characterized in that, Includes the following steps: Obtain the dimensional data of each preset dimension collected at each moment within the current observation period corresponding to the current moment to be adjusted; Based on the dimension data collected at different times under the same preset dimension, the target anomaly dimension corresponding to each time moment is selected from all preset dimensions, and the target anomaly time period under each target anomaly dimension corresponding to each time moment is obtained. Based on the dimensional data of the target anomaly period under the corresponding different target anomaly dimensions at each time point, determine the degree of indoor air deterioration at each time point; Based on the degree of indoor air deterioration at different times within the current observation period, clusters are formed at different times within the current observation period to obtain target clusters, and target time periods are obtained based on the continuous times within each target cluster. Based on all target anomaly dimensions and indoor air deterioration levels at different times within all target time periods, determine the overall air anomaly index corresponding to the current time to be adjusted; Based on the overall air quality anomaly index corresponding to the current time to be adjusted, the fan airflow is adjusted and controlled at the current time to be adjusted.

2. The intelligent air volume control method for a fresh air system according to claim 1, characterized in that, The step of filtering out the target abnormal dimension corresponding to each time moment from all preset dimensions based on dimensional data collected at different times under the same preset dimension includes: Based on the dimension data of the same preset dimension collected at different times, determine the abnormal candidate time corresponding to each preset dimension; Filter out the target abnormal moment corresponding to each preset dimension from all candidate abnormal moments corresponding to each preset dimension; The preset dimension is defined as the target anomaly dimension corresponding to each target anomaly moment.

3. The intelligent air volume control method for a fresh air system according to claim 2, characterized in that, The step of determining the abnormal candidate time corresponding to each preset dimension based on dimensional data collected at different times under the same preset dimension includes: Any moment within the current observation period is designated as the marked moment, and the moment preceding the marked moment is designated as the reference moment. Any preset dimension is designated as the marked dimension. If the difference between the dimension data of the marked dimension collected at the marked time and the dimension data of the marked dimension collected at the reference time is greater than a preset difference threshold, then the marked time is determined as an abnormal candidate time corresponding to the marked dimension.

4. The intelligent air volume control method for a fresh air system according to claim 2, characterized in that, The step of selecting the target abnormal moment corresponding to each preset dimension from all candidate abnormal moments corresponding to each preset dimension includes: Any preset dimension is determined as the label dimension, and the continuous abnormal candidate moments corresponding to the label dimension constitute the abnormal candidate time period corresponding to the label dimension. Based on the duration of each abnormal candidate time period corresponding to the labeled dimension, and the maximum value and range of all dimension data under the labeled dimension collected within each abnormal candidate time period corresponding to the labeled dimension, the degree of sudden change in air quality corresponding to each abnormal candidate time period corresponding to the labeled dimension is determined. If the degree of air quality change in the abnormal candidate time period corresponding to the marked dimension is greater than the preset air quality change threshold, then each moment in the abnormal candidate time period is determined as the target abnormal moment corresponding to the marked dimension.

5. The intelligent air volume control method for a fresh air system according to claim 2, characterized in that, The process of obtaining the target anomaly time period for each moment under each corresponding target anomaly dimension includes: Any moment within the current observation period is designated as the marked moment, and any target anomaly dimension corresponding to the marked moment is designated as the marked anomaly dimension. The target abnormal times that are continuous with the marked time among all the target abnormal times corresponding to the marked abnormal dimension constitute the target abnormal time period under the marked abnormal dimension.

6. The intelligent air volume control method for a fresh air system according to claim 4, characterized in that, The step of determining the degree of indoor air deterioration at each moment based on the dimensional data of the target anomaly period under its corresponding different target anomaly dimensions includes: Any moment within the current observation period is designated as the marked moment. If the number of target anomaly dimensions corresponding to the marked moment is 0, then the indoor air deterioration degree corresponding to the marked moment is set to a constant of 0. If the number of target anomaly dimensions corresponding to the marked time is 1, then the indoor air deterioration degree corresponding to the marked time is set to a constant of 0.1; If the number of target anomaly dimensions corresponding to the marked time is greater than 1, then based on the correlation between the dimensional data of the marked time in the target anomaly time period under different target anomaly dimensions, the degree of change of the marked time under each target anomaly dimension is determined. Based on the degree of change of the marked time under different target anomaly dimensions, the degree of sudden change in air quality corresponding to the anomaly candidate time period to which the marked time belongs among all anomaly candidate time periods corresponding to different target anomaly dimensions, and the number of target anomaly dimensions corresponding to the marked time, the degree of indoor air deterioration corresponding to the marked time is determined.

7. The intelligent air volume control method for a fresh air system according to claim 6, characterized in that, The step of determining the degree of influence of the change of the marked time in each target anomaly dimension based on the correlation between the dimensional data of the marked time in the target anomaly time period under different target anomaly dimensions includes: The initial abnormal data sequence for each target abnormal time period under each target abnormal dimension at the marked time is formed by taking all the dimension data of the target abnormal time period under each target abnormal dimension at the marked time. Interpolation processing is performed on the initial abnormal data sequences of the marked time under different target abnormality dimensions to obtain the target abnormal data sequences of the marked time under different target abnormality dimensions, wherein the number of elements in the different target abnormality data sequences is the same; The degree of simultaneous change between each pair of target anomaly dimensions at the marked time is determined based on the number of elements in the initial anomaly data sequence at each pair of target anomaly dimensions at the marked time, and the Pearson correlation coefficient between the target anomaly data sequences at each pair of target anomaly dimensions at the marked time. The mean of the degree of simultaneous change of the marked time in each of its corresponding target anomaly dimensions and all other target anomaly dimensions is determined as the degree of influence of the change of the marked time in each of its corresponding target anomaly dimensions.

8. The intelligent air volume control method for a fresh air system according to claim 1, characterized in that, The process involves determining the overall air quality anomaly index corresponding to the current time to be adjusted based on all target anomaly dimensions and indoor air quality deterioration levels at different times within all target time periods, including: All target anomaly dimensions corresponding to each time moment constitute the target anomaly dimension set corresponding to each time moment; Based on the intersection of the target anomaly dimension sets corresponding to different times within each target time period, each target time period is divided into sub-time periods. Based on the duration of different sub-periods within each target period and the number of elements in the intersection of the target anomaly dimension sets corresponding to all times within each sub-period of each target period, the complex air anomaly index corresponding to each target period is determined. Based on the complex air quality indicators corresponding to each target time period and the average indoor air quality deterioration at all times within each target time period, the air quality indicators corresponding to each target time period are determined. Select the period with the lowest corresponding air quality index from all target periods and use it as a reference period; If the air quality index corresponding to the target time period is less than or equal to the preset quality threshold, then the target time period will be determined as a period with poor air quality. Based on the cumulative value of the durations corresponding to all periods with poor air quality, the air quality index corresponding to the reference period, and the duration between the end time of the reference period and the current time to be adjusted, the overall air quality anomaly index corresponding to the current time to be adjusted is determined.

9. The intelligent air volume control method for a fresh air system according to claim 8, characterized in that, The process involves segmenting each target time period into sub-time periods based on the intersection of the target anomaly dimension sets corresponding to different times within each target time period. This sub-time period includes: If the intersection between the target anomaly dimension sets corresponding to two adjacent time points is empty, then the later of these two time points is determined as the temporary time point; Each target time period is divided into sub-time periods by using temporary moments within each target time period as dividing points.

10. An intelligent airflow control device for a fresh air system, characterized in that, It includes a processor and a memory, the processor being used to process instructions stored in the memory to implement a method for intelligent airflow control of a fresh air system according to any one of claims 1-9.

Images