An intelligent control method and device for air volume of a fresh air system

Abstract

The present application relates to the technical field of air volume regulation, and particularly relates to an air volume intelligent control method and device for a fresh air system, which comprises the following steps: obtaining dimension data in each preset dimension collected at each time in a current observation time period corresponding to a current to-be-regulated time; screening out a target abnormal dimension corresponding to each time and obtaining a target abnormal time period in each target abnormal dimension corresponding to each time; determining an indoor air deterioration degree corresponding to each time; clustering different times in the current observation time period and obtaining a target time period; determining an overall air abnormality index corresponding to the current to-be-regulated time according to all target abnormal dimensions and indoor air deterioration degrees corresponding to different times in all target time periods; and adjusting and controlling the fan air volume at the current to-be-regulated time. The present application realizes self-adaptive adjustment of the fan air volume of the fresh air system and improves the rationality of fan air volume control adjustment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air volume regulation, in particular to an air volume intelligent control method and device of a fresh air system. BACKGROUND

[0002] The fresh air system is an indoor ventilation and air exchange equipment, wherein a fresh air host is connected with an air distributor in the room through a pipeline, and relies on mechanical initiative to send indoor and outdoor air to the room to form a "fresh air flow field" in the room space, which can discharge indoor polluted air to the outdoor while introducing fresh outdoor air into the room, thereby meeting the needs of indoor fresh air exchange. At present, when controlling the air volume, the commonly used method is that the fan is usually operated in a fixed air volume mode to realize motor air volume control.

[0003] However, when the fan in the fresh air system is operated in a fixed air volume mode to realize air volume control, the following technical problems often exist:

[0004] In actual situations, the air quality in the room at different times is often different, and different indoor air quality requires different air volume, so when the fan air volume at different times is set to a fixed air volume, the rationality of fan air volume control and adjustment is poor, thereby it is difficult to adaptively adjust the indoor air quality. SUMMARY

[0005] In order to solve the technical problem of poor rationality of fan air volume control and adjustment, the present application provides an air volume intelligent control method and device of a fresh air system.

[0006] In a first aspect, the present application provides an air volume intelligent control method of a fresh air system, which comprises:

[0007] Obtaining dimension data in each preset dimension collected at each time in a current observation time period corresponding to a current to-be-adjusted time;

[0008] According to the dimension data in the same preset dimension collected at different times, the target abnormal dimension corresponding to each time is screened from all preset dimensions, and the target abnormal time period in each target abnormal dimension corresponding to each time is obtained;

[0009] According to the dimension data in the target abnormal time period in each target abnormal dimension corresponding to each time, the indoor air deterioration degree corresponding to each time is determined;

[0010] cluster different time instants in the current observation time period according to the indoor air deterioration degrees corresponding to the different time instants in the current observation time period, to obtain target clusters, and obtain a target time period based on continuous time instants in each target cluster;

[0011] determine an overall air abnormality index corresponding to the current to-be-adjusted time instant according to all target abnormality dimensions corresponding to different time instants in all target time periods and the indoor air deterioration degrees;

[0012] adjust and control the fan air volume at the current to-be-adjusted time instant according to the overall air abnormality index corresponding to the current to-be-adjusted time instant.

[0013] In a possible implementation manner of the first aspect, the determining of the target abnormality dimension corresponding to each time instant from all preset dimensions according to the dimension data of the same preset dimension collected at different time instants comprises:

[0014] determining an abnormality candidate time instant corresponding to each preset dimension according to the dimension data of the same preset dimension collected at different time instants;

[0015] screening a target abnormality time instant corresponding to the preset dimension from all abnormality candidate time instants corresponding to the preset dimension;

[0016] determining the preset dimension as the target abnormality dimension corresponding to each target abnormality time instant corresponding to the preset dimension.

[0017] In a possible implementation manner of the first aspect, the determining of the abnormality candidate time instant corresponding to each preset dimension according to the dimension data of the same preset dimension collected at different time instants comprises:

[0018] determining any one time instant in the current observation time period as a marker time instant, determining a time instant before the marker time instant as a reference time instant, and determining any one preset dimension as a marker dimension;

[0019] if a difference between the dimension data of the marker dimension collected at the marker time instant and the dimension data of the marker dimension collected at the reference time instant is greater than a preset difference threshold, determining the marker time instant as an abnormality candidate time instant corresponding to the marker dimension.

[0020] In a possible implementation manner of the first aspect, the screening of the target abnormality time instant corresponding to the preset dimension from all abnormality candidate time instants corresponding to the preset dimension comprises:

[0021] determining any one preset dimension as a marker dimension, and constructing abnormality candidate time periods corresponding to the marker dimension by using continuous abnormality candidate time instants corresponding to the marker dimension;

[0022] determine the air quality sudden change degree corresponding to each abnormal candidate time period of the marker dimension according to the length of time corresponding to each abnormal candidate time period of the marker dimension, and the maximum value and range of all dimension data under the marker dimension collected in each abnormal candidate time period of the marker dimension;

[0023] If the air quality sudden change degree corresponding to the abnormal candidate time period of the marker dimension is greater than a preset quality sudden change threshold, each time point in the abnormal candidate time period is determined as a target abnormal time point corresponding to the marker dimension.

[0024] In combination with the first aspect, in a possible implementation, the acquiring of the target abnormal time period of each time point under each target abnormal dimension corresponding thereto includes:

[0025] determining any one time point in the current observation time period as a marker time point, and determining any one target abnormal dimension corresponding to the marker time point as a marker abnormal dimension;

[0026] constituting the target abnormal time period of the marker time point under the marker abnormal dimension from the target abnormal time points that are continuous to the marker time point among all target abnormal time points corresponding to the marker abnormal dimension.

[0027] In combination with the first aspect, in a possible implementation, the determining of the indoor air deterioration degree corresponding to each time point according to the dimension data in the target abnormal time period of each time point under different target abnormal dimensions corresponding thereto includes:

[0028] determining any one time point in the current observation time period as a marker time point, and setting the indoor air deterioration degree corresponding to the marker time point as a constant 0 if the number of target abnormal dimensions corresponding to the marker time point is 0;

[0029] setting the indoor air deterioration degree corresponding to the marker time point as a constant 0.1 if the number of target abnormal dimensions corresponding to the marker time point is 1;

[0030] If the number of target abnormal dimensions corresponding to the marker time point is greater than 1, determining the change influence degree of the marker time point under each target abnormal dimension corresponding thereto according to the correlation between the dimension data in the target abnormal time period of the marker time point under different target abnormal dimensions corresponding thereto, and determining the indoor air deterioration degree corresponding to the marker time point based on the change influence degree of the marker time point under different target abnormal dimensions corresponding thereto, the air quality sudden change degree corresponding to the abnormal candidate time period of the marker time point in the abnormal candidate time period corresponding to all abnormal candidate time periods corresponding to different target abnormal dimensions of the marker time point, and the number of target abnormal dimensions corresponding to the marker time point.

[0031] 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:

[0032] 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.

[0033] 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;

[0034] 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.

[0035] 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.

[0036] 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:

[0037] All target anomaly dimensions corresponding to each time moment constitute the target anomaly dimension set corresponding to each time moment;

[0038] 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.

[0039] 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.

[0040] determine an air quality index corresponding to each target period according to the air anomaly complexity index corresponding to each target period and the mean value of the indoor air deterioration degree corresponding to each time in each target period;

[0041] select a target period corresponding to the minimum air quality index from all target periods as a reference period;

[0042] if the air quality index corresponding to the target period is less than or equal to a preset quality threshold, determine the target period as a poor quality period;

[0043] determine an overall air anomaly index corresponding to the current to-be-adjusted time according to the cumulative value of the lengths of all poor quality periods, the air quality index corresponding to the reference period, and the length between the end time of the reference period and the current to-be-adjusted time.

[0044] In a possible implementation manner of the first aspect, the dividing each target period to obtain a sub-period according to the intersection of the target anomaly dimension sets corresponding to different times in each target period comprises:

[0045] if the intersection between the target anomaly dimension sets corresponding to two adjacent times is empty, determine the later time of the two times as a temporary time;

[0046] divide each target period to obtain a sub-period by taking the temporary time in each target period as a division point.

[0047] In the second aspect, the present application provides a fresh air system air volume intelligent control device, comprising a processor and a memory, the processor is used for processing the instructions stored in the memory to realize the method in the first aspect or any one of the possible implementation manners of the first aspect, specifically, the device comprises:

[0048] a dimension data acquisition module, configured to acquire dimension data of each preset dimension collected at each time in a current observation period corresponding to a current to-be-adjusted time;

[0049] a screening and acquisition module, configured to screen a target anomaly dimension corresponding to each time from all preset dimensions according to the dimension data of a same preset dimension collected at different times, and acquire a target anomaly period of each time in each target anomaly dimension corresponding to the time;

[0050] an indoor air deterioration degree determination module, configured to determine an indoor air deterioration degree corresponding to each time according to the dimension data in the target anomaly period of each target anomaly dimension corresponding to the time;

[0051] The clustering and obtaining module is configured to cluster different time points in the current observation time period according to the indoor air deterioration degree corresponding to the different time points, obtain target clusters, and obtain target time periods based on continuous time points in each target cluster.

[0052] The overall air anomaly index determination module is configured to determine an overall air anomaly index corresponding to the current time point to be adjusted according to all target anomaly dimensions and the indoor air deterioration degree corresponding to different time points in all target time periods.

[0053] The air volume regulation control module is configured to regulate and control the air volume of the fan at the current time point to be adjusted according to the overall air anomaly index corresponding to the current time point to be adjusted.

[0054] In a third aspect, a server is provided, including a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation manner of the first aspect.

[0055] In a fourth aspect, a computer program product is provided, which includes computer program code. When the computer program code is run on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0056] In a fifth aspect, a computer readable storage medium is provided, which stores computer program code. When the computer program code is run on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0057] The present application has the following beneficial effects:

[0058] The air volume intelligent control method of the fresh air system provided by the present application realizes self-adaptive regulation of the fan air volume of the fresh air system, solves the technical problem of poor rationality of fan air volume control and regulation, and improves the rationality of fan air volume control and regulation. Specifically, the present application quantifies a plurality of indexes related to the current indoor environment, such as indoor air deterioration degree and overall air anomaly index, by analyzing dimension data in different preset dimensions in the current observation time period, thereby realizing regulation and control of the fan air volume at the current time point to be adjusted and improving the rationality of fan air volume control and regulation of the fresh air system. BRIEF DESCRIPTION OF DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings required in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flow chart of a fresh air system air volume intelligent control method of the present application;

[0061] Figure 2 A component structure schematic diagram of a fresh air system air volume intelligent control device of the present application;

[0062] Figure 3 A structure schematic diagram of a computer device of the present application. DETAILED DESCRIPTION

[0063] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of the technical solutions according to the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0064] 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 the present application belongs.

[0065] Reference Figure 1 , shows the flow of some embodiments of a fresh air system air volume intelligent control method of the present application. The fresh air system air volume intelligent control method comprises the following steps:

[0066] Step S1, obtaining the dimension data in each preset dimension collected at each time in the current observation time period corresponding to the current to be adjusted time.

[0067] The current to-be-adjusted time point can be a time point at which air volume adjustment is to be performed currently. The current observation time period can be a time period ending at the current to-be-adjusted time point, which can be used to observe the current indoor environment change, and can assist in air volume adjustment at the current to-be-adjusted time point. The length of the current observation time period can be 1 hour. The preset dimension can be a dimension that is pre-set to affect the indoor environment quality. The number of preset dimensions can be pre-set, and can be 5. For example, the preset dimensions can include, but are not limited to, a carbon dioxide concentration dimension, a carbon monoxide concentration dimension, a formaldehyde concentration dimension, a PM2.5 concentration dimension, and an ozone concentration dimension. The dimension data under the preset dimension can be a normalized value of the preset dimension value. For example, the dimension data under the carbon dioxide concentration dimension can be a normalized value of the indoor carbon dioxide concentration.

[0068] For example, taking the carbon dioxide concentration dimension as an example, a method for obtaining the dimension data under the carbon dioxide concentration dimension collected at each time point in the current observation time period corresponding to the current to-be-adjusted time point can be that, in the current observation time period, the indoor carbon dioxide concentration is collected every 1 second by a carbon dioxide concentration sensor, and the normalized value of the indoor carbon dioxide concentration collected each time is recorded as the dimension data under the carbon dioxide concentration dimension.

[0069] Step S2: From all the preset dimensions, a target abnormal dimension corresponding to each time point is selected according to the dimension data under the same preset dimension collected at different time points, and a target abnormal time period under each target abnormal dimension corresponding to each time point is obtained.

[0070] For example, the present step can include the following steps:

[0071] First, determining an abnormal candidate time point corresponding to each preset dimension according to the dimension data under the same preset dimension collected at different time points can include the following steps:

[0072] First sub-step, determining any one time point in the above current observation time period as a marked time point, and determining a time point before the above marked time point as a reference time point, and determining any one preset dimension as a marked dimension.

[0073] Second sub-step, if the difference between the dimension data under the above marked dimension collected at the above marked time point and the dimension data under the above marked dimension collected at the above reference time point is greater than a preset difference threshold, the above marked time point is determined as an abnormal candidate time point corresponding to the above marked dimension.

[0074] The preset difference threshold can be a pre-set threshold, which can be 0.3.

[0075] It should be noted that, under normal circumstances, the indoor environment data of various dimensions changes relatively slowly, if the data suddenly appears a large abnormal change (i.e. the absolute value of the difference is large), it may mean that some activities are being carried out in the room, such as cooking or gathering of many people, etc., resulting in a sharp increase in carbon dioxide and oil smoke in the room. At this time, it is often necessary to increase the air volume in time and introduce fresh air to ensure air quality.

[0076] Secondly, the target abnormal moment corresponding to each preset dimension is screened from all abnormal candidate moments corresponding to the preset dimension, which can include the following sub-steps:

[0077] The first sub-step is to determine any one of the preset dimensions as a marker dimension, and to form an abnormal candidate time period corresponding to the marker dimension from the continuous abnormal candidate moments corresponding to the marker dimension.

[0078] For example, if the abnormal candidate moments corresponding to the marker dimension are 11, the 11 abnormal candidate moments 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 time length between adjacent data collection moments is 1 second, then the abnormal candidate time period corresponding to the marker dimension can have 3, and the 3 abnormal 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.

[0079] The second sub-step is to determine the air quality sudden change degree corresponding to each abnormal candidate time period of the marker dimension according to the time length corresponding to each abnormal candidate time period of the marker dimension, and the maximum value and range of all dimension data under the marker dimension collected in each abnormal candidate time period of the marker dimension.

[0080] For example, any one of the abnormal candidate time periods corresponding to the marker dimension is determined as a marker candidate time period, and the formula for determining the air quality sudden change degree corresponding to the marker candidate time period can be:

[0081] ;

[0082] Wherein, b is the air quality sudden change degree corresponding to the marker candidate time period. is a normalization function. t is the duration of the label candidate time period, which is equal to the duration between the start time and the end time of the label candidate time period. c is the maximum value of all dimension data in the label dimension collected in the label candidate time period. L is the range of all dimension data in the label dimension collected in the label candidate time period.

[0083] It should be noted that when t is larger, it often indicates that there are more abnormal candidate time points in the label candidate time period, and it often indicates that there may be more data in the label dimension that is abnormal in the label candidate time period. When c is larger, it often indicates that the label candidate time period is more likely to be abnormal. When L is larger, it often indicates that the fluctuation range of the label dimension data in the label candidate time period is larger, and it is more likely to be abnormal. Therefore, when b is larger, it often indicates that the label dimension is more likely to cause the indoor environment quality to deteriorate in the label candidate time period.

[0084] The third sub-step is to determine each time point in the abnormal candidate time period as a target abnormal time point corresponding to the label dimension if the air quality sudden change degree corresponding to the abnormal candidate time period corresponding to the label dimension is greater than a preset quality sudden change threshold.

[0085] The preset quality sudden change threshold can be a threshold set in advance, which can be 0.7.

[0086] The third step is to determine a preset dimension as a target abnormal dimension corresponding to each target abnormal time point corresponding to the preset dimension.

[0087] The target abnormal time point corresponding to the target abnormal dimension often represents the dimension that has an abnormal fluctuation at the target abnormal time point.

[0088] For example, if a target abnormal time point corresponding to the carbon dioxide concentration dimension is 9: 86 seconds, the carbon dioxide concentration dimension can be a target abnormal dimension corresponding to 9: 86 seconds.

[0089] It should be noted that the same preset dimension can correspond to multiple different target abnormal time points, and the same time point can correspond to multiple target abnormal dimensions.

[0090] The fourth step is to determine any time point in the current observation time period as a label time point, and determine any target abnormal dimension corresponding to the label time point as a label abnormal dimension.

[0091] The fifth step is to construct a target abnormal time period of the label time point in the label abnormal dimension from the target abnormal time points corresponding to the label abnormal dimension that are continuous with the label time point.

[0092] For example, if the target abnormal time corresponding to the marked abnormal dimension has 7 target abnormal times, which are 9:10:2, 9:10:3, 9:10:4, 9:10:5, 9:10:6, 9:20:8, and 9:20:9, and the marked time is 9:10:4, then the target abnormal period of the marked time under the marked abnormal dimension can be a time period with 9:10:2 as the start time and 9:10:6 as the end time.

[0093] Step S3, determining the indoor air deterioration degree corresponding to each time according to the dimension data of each time within the target abnormal period of each time under the corresponding different target abnormal dimension.

[0094] It should be noted that in actual cases, the more target abnormal dimensions corresponding to the same time, the more dimension data that is abnormal at that time, the more dimension characteristics that affect the indoor environment at that time, and the more likely the air quality at that time is poor. In addition, one typical feature of indoor environmental quality is multi-factor correlation and synergistic deterioration, so the more target abnormal dimensions corresponding to the same time and the higher the correlation between the target abnormal dimensions, the more likely it is to cause poor air quality at that time.

[0095] As an example, the present step can include the following steps:

[0096] First, any time within the current observation period is determined as a marked time, and if the number of target abnormal dimensions corresponding to the marked time is 0, the indoor air deterioration degree corresponding to the marked time is set to a constant 0.

[0097] Second, if the number of target abnormal dimensions corresponding to the marked time is 1, the indoor air deterioration degree corresponding to the marked time is set to a constant 0.1.

[0098] Third, if the number of target abnormal dimensions corresponding to the marked time is greater than 1, determining the indoor air deterioration degree corresponding to the marked time according to the dimension data of the marked time within the target abnormal period of each target abnormal dimension corresponding to the marked time can include the following sub-steps:

[0099] First sub-step, determining the change influence degree of the marked time under each target abnormal dimension corresponding to the marked time according to the correlation between the dimension data of the marked time within the target abnormal period of each target abnormal dimension corresponding to the marked time can include the following steps:

[0100] Firstly, all the dimension data of the target abnormal period of the marking time in each target abnormal dimension corresponding to the marking time is constructed into an initial abnormal data sequence of the marking time in each target abnormal dimension corresponding to the marking time.

[0101] The initial abnormal data sequence can be a time sequence.

[0102] Then, the initial abnormal data sequences of the marking time in different target abnormal dimensions corresponding to the marking time are processed by a polynomial interpolation algorithm to obtain target abnormal data sequences of the marking time in different target abnormal dimensions corresponding to the marking time.

[0103] The number of elements in the different target abnormal data sequences can be the same. The target abnormal data sequence can be the initial abnormal data sequence after the interpolation processing.

[0104] It should be noted that the initial abnormal data sequences of the marking time in different target abnormal dimensions corresponding to the marking time are processed by the interpolation algorithm mainly to interpolate the number of elements in different initial abnormal data sequences to be consistent, mainly to facilitate subsequent calculation of the correlation between different initial abnormal data sequences.

[0105] Then, according to the number of elements in the initial abnormal data sequences of the marking time in each two target abnormal dimensions corresponding to the marking time and the Pearson correlation coefficients between the target abnormal data sequences of the marking time in each two target abnormal dimensions corresponding to the marking time, the simultaneous change degree between each two target abnormal dimensions corresponding to the marking time is determined.

[0106] The Pearson correlation coefficients between different target abnormal data sequences can represent the correlation between different initial abnormal data sequences.

[0107] For example, the formula for determining the simultaneous change degree between different target abnormal dimensions corresponding to the marking time can be:

[0108] ;

[0109] ;

[0110] ;

[0111] wherein, is the simultaneous change degree between the i th target abnormal dimension and the j th target abnormal dimension corresponding to the marking time. i and j are the serial numbers of different target abnormal dimensions corresponding to the marking time. is a normalization function. is the minimum initial abnormal data quantity between the i-th target abnormal dimension and the j-th target abnormal dimension corresponding to the marked time. is an exponential function with a natural constant as the base. is the maximum initial abnormal data quantity between the i-th target abnormal dimension and the j-th target abnormal dimension corresponding to the marked time. is the Pearson correlation coefficient between the target abnormal data sequence in the i-th target abnormal dimension and the target abnormal data sequence in the j-th target abnormal dimension corresponding to the marked time. is a minimum value function. is a maximum value function. is the number of elements in the initial abnormal data sequence in the i-th target abnormal dimension corresponding to the marked time. is the number of elements in the initial abnormal data sequence in the j-th target abnormal dimension corresponding to the marked time.

[0112] It should be noted that, when is greater, it often means that the minimum number of elements in the initial abnormal data sequence in the i-th target abnormal dimension and the j-th target abnormal dimension corresponding to the marked time is greater, it often means that the i-th target abnormal dimension and the j-th target abnormal dimension originally participate in the element calculation of the Pearson correlation coefficient, it often means that the calculated is more reliable. When is greater, it often means that more data is supplemented by the interpolation algorithm, it often means that the calculated is less reliable. When is greater, it often means that there is a certain correlation between the i-th target abnormal dimension and the j-th target abnormal dimension at the marked time, it often means that there is a possibility of synergistic deterioration between the i-th target abnormal dimension and the j-th target abnormal dimension at the marked time. Therefore, when is greater, it often means that there is a possibility of synergistic deterioration between the i-th target abnormal dimension and the j-th target abnormal dimension at the marked time.

[0113] Finally, the average of the simultaneous change degree between each target abnormal dimension corresponding to the marked time and all other target abnormal dimensions is determined as the change influence degree of each target abnormal dimension corresponding to the marked time.

[0114] For example, the formula corresponding to the change influence degree of different target abnormal dimensions corresponding to the marked time can be:

[0115] ;

[0116] wherein, is the change impact degree of the marked time in its corresponding ith target abnormal dimension. i and j are the serial numbers of different target abnormal dimensions corresponding to the marked time. N is the number of target abnormal dimensions corresponding to the marked time. is the simultaneous change degree of the marked time between its corresponding ith target abnormal dimension and jth target abnormal dimension.

[0117] It should be noted that when is greater, it often indicates that there is a certain correlation between the ith target abnormal dimension and other target abnormal dimensions at the marked time, and often indicates that there is a synergistic deterioration between the ith target abnormal dimension and other target abnormal dimensions at the marked time.

[0118] The second sub-step is to determine the formula corresponding to the indoor air deterioration degree corresponding to the marked time based on the change impact degree of the marked time in its corresponding different target abnormal dimensions, the air quality sudden change degree of the abnormal candidate time period corresponding to the marked time belonging to all abnormal candidate time periods corresponding to the different target abnormal dimensions corresponding to the marked time, and the number of target abnormal dimensions corresponding to the marked time. The formula can be:

[0119] ;

[0120] E is the indoor air deterioration degree corresponding to the marked time, and its value range can be [0.2, 1]. is a normalization function. N is the number of target abnormal dimensions corresponding to the marked time. n is the number of preset dimensions. i is the serial number of the target abnormal dimension corresponding to the marked time. is the change impact degree of the marked time in its corresponding ith target abnormal dimension. is the air quality sudden change degree of the abnormal candidate time period corresponding to the marked time belonging to all abnormal candidate time periods corresponding to the ith target abnormal dimension corresponding to the marked time.

[0121] It should be noted that when is greater, it often indicates that there are more types of environmental dimensions that appear abnormal at the marked time. When is greater, it often indicates that the ith target abnormal dimension is more likely to cause indoor environmental quality to deteriorate at the marked time. When is greater, it often indicates that there is a certain correlation between the ith target abnormal dimension and other target abnormal dimensions at the marked time, and often indicates that there is a synergistic deterioration between the ith target abnormal dimension and other target abnormal dimensions at the marked time. Therefore, E can represent the indoor air deterioration degree at the marked time, and the greater the value, the worse the indoor air quality at the marked time, and the greater the air volume required for indoor air conditioning.

[0122] Step S4, according to the indoor air deterioration degree corresponding to different time in the current observation period, clustering the different time in the current observation period, obtaining the target cluster, and based on the continuous time in each target cluster, obtaining the target period.

[0123] It should be noted that in actual situation, the abnormality of indoor environment often presents "sustained scene characteristics" (such as dinner cooking period, etc.), and the comprehensive abnormality degree of a single time may fluctuate slightly due to instantaneous disturbance (such as suddenly opening the door, etc.). If the air volume is directly adjusted according to the comprehensive abnormality degree of each time, the air volume will often change frequently, which not only increases the equipment loss, but also may affect the indoor comfort due to the sudden change of air volume. Therefore, the embodiment of the present application adjusts the air volume by analyzing the overall environmental change in the current observation period. The previous air volume adjustment time of the current to-be-adjusted time can be the previous time of the current observation period.

[0124] Among them, the target period can represent a sustained abnormal period, an instantaneous disturbance abnormal period or a normal period.

[0125] As an example, the present step can include the following steps:

[0126] First, according to the indoor air deterioration degree corresponding to different time in the current observation period, clustering the different time in the current observation period, obtaining the target cluster.

[0127] For example, according to the indoor air deterioration degree corresponding to different time in the current observation period, clustering the different time in the current observation period by DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, and recording each clustering cluster obtained at this time as the target cluster.

[0128] Second, based on the continuous time in each target cluster, obtaining the target period.

[0129] For example, if there are 11 time points in a target cluster, the 11 time points are 9:11:1, 9:11:2, 9:11:3, 9:11:4, 9:18:6, 9:18:7, 9:18:8, 9:40:20, 9:40:21, 9:40:22, and 9:40:23, and the time interval between adjacent data collection time points is 1 second, then 3 target time periods can be obtained, which are a time period starting at 9:11:1 and ending at 9:11:4, a time period starting at 9:18:6 and ending at 9:18:8, and a time period starting at 9:40:20 and ending at 9:40:23.

[0130] In step S5, the overall air abnormality index corresponding to the current time to be adjusted is determined according to all target abnormal dimensions corresponding to different time points in all target time periods and the indoor air deterioration degree.

[0131] It should be noted that in actual situations, the cause of poor indoor air quality may not be single, for example, in some periods, the temperature and humidity and other dimensional environmental data may be abnormal due to cooking, while in other periods, the carbon dioxide and formaldehyde content in the air may rise due to a large number of people gathering or decoration. In each target time period, if the type of abnormal data is stable, it means that the cause of poor air quality is relatively single, the type of environmental data affected is less, and the impact on air quality is small. If the type of abnormal data changes constantly, it means that the cause of poor air quality may be more diverse, which may indicate that the cause of abnormality is more likely to be diversified, and the impact on air quality is large, so it is necessary to increase the air volume adjustment at this time.

[0132] As an example, the present step can include the following steps:

[0133] Firstly, all target abnormal dimensions corresponding to each time point are constructed to form a target abnormal dimension set corresponding to each time point.

[0134] Secondly, each target time period is segmented according to the intersection of the target abnormal dimension sets corresponding to different time points in each target time period to obtain a sub-period, which can include the following sub-steps:

[0135] First sub-step, if the intersection between the target abnormal dimension sets corresponding to two adjacent time points is empty, then the later time point of the two time points is determined as a temporary time point.

[0136] Second sub-step, each target time period is segmented with the temporary time point in each target time period as a segmentation point to obtain a sub-period.

[0137] It should be noted that the data dimension type appearing abnormally in the sub-period is relatively stable.

[0138] In the third step, according to the length of each sub-period corresponding to each target period, and the number of elements in the intersection of the target abnormal dimension sets corresponding to all time points in each sub-period in each target period, the air abnormal complexity index corresponding to each target period is determined.

[0139] For example, the formula corresponding to the air abnormal complexity index corresponding to the target period can be:

[0140] ;

[0141] Wherein, is the air abnormal complexity index corresponding to the mth target period. m is the serial number of the target period. is the exponential function with a natural constant as the base. is the number of sub-periods in the mth target period. a is the serial number of the sub-period in the mth target period. is the length of the a th sub-period corresponding to the mth target period. is the number of elements in the intersection of the target abnormal dimension sets corresponding to all time points in the a th sub-period in the mth target period. is the number of elements in the union of the target abnormal dimension sets corresponding to all time points in the a th sub-period in the mth target period.

[0142] It should be noted that when is smaller, it often means that the length of the sub-period in the mth target period is smaller, it often means that the maintenance time of the same abnormal dimension in the mth target period is relatively shorter, it often means that the dimension type of the abnormal data in the mth target period is more likely to change, and it often means that the reason for the abnormal data in the mth target period is more likely to be diversified. When is larger, it often means that the abnormal dimension at different time points in the a th sub-period is more likely to be the same, and it often means that the data dimension type appearing abnormally in the a th sub-period is relatively stable. Conversely, when is smaller, it often means that the data dimension type appearing abnormally in the a th sub-period is relatively unstable, and the reason for the poor air quality in the a th sub-period is often more complex. Therefore, when is larger, it often means that the data dimension type appearing abnormally in the mth target period is relatively unstable, and the reason for the poor air quality in the mth target period is often more complex.

[0143] Fourthly, the air quality index corresponding to each target period is determined according to the air anomaly complexity index corresponding to each target period and the average of the indoor air deterioration degree corresponding to all time points in each target period.

[0144] For example, the formula for determining the air quality index corresponding to the target period can be:

[0145] ;

[0146] is the air quality index corresponding to the mth target period. m is the serial number of the target period. is an exponential function with a natural constant as the base. is the air anomaly complexity index corresponding to the mth target period. is the average of the indoor air deterioration degree corresponding to all time points in the mth target period.

[0147] It should be noted that, can represent the indoor air deterioration degree in the mth target period. The larger the value, the worse the indoor air quality in the mth target period, and the greater the air volume required for indoor air conditioning. When is larger, the data dimension type that is abnormal in the mth target period is relatively less stable, and the reason for the poor air quality in the mth target period is relatively more complex. Therefore, when is larger, the indoor air quality in the mth target period is relatively better.

[0148] Fifthly, the target period with the smallest air quality index is selected from all target periods as the reference period.

[0149] Sixthly, if the air quality index corresponding to the target period is less than or equal to the preset quality threshold, the target period is determined as a poor quality period.

[0150] The preset quality threshold can be a pre-set threshold, which can be 0.7.

[0151] Seventhly, the overall air anomaly index corresponding to the current to-be-adjusted time point is determined according to the cumulative value of the lengths of all poor quality periods, the air quality index corresponding to the reference period, and the length of time between the end time point of the reference period and the current to-be-adjusted time point.

[0152] For example, the formula for determining the overall air anomaly index corresponding to the current to-be-adjusted time point can be:

[0153] ;

[0154] ​Q is the overall air abnormality index corresponding to the current time to be adjusted. is the cumulative value of the time length corresponding to all poor quality periods. is the time length corresponding to the current observation period. is the exponential function with a natural constant as the base. p is the air quality index corresponding to the reference period. k is the time length between the end time of the reference period and the current time to be adjusted.

[0155] It should be noted that in actual situations, the change of indoor air quality often has a delay and may be affected by sudden events (such as sudden changes in human flow, internal activities, etc.). Therefore, when adjusting the air volume at the current time to be adjusted, simply relying on the air quality index in a local period at a certain time may not reflect the actual situation of the current air quality. Therefore, the air quality of historical multiple poor air quality periods and the potential impact on future air quality are also considered to improve the accuracy of system air volume adjustment and maintain the stability and comfort of the indoor environment. When p is smaller, it often means that the indoor air quality in the reference period is relatively worse, and it often means that there is a period of poor indoor air quality in the current observation period. When k is smaller, it often means that the period of poor indoor air quality in the current observation period is closer to the current time to be adjusted, and it often means that the period of poor indoor air quality in the current observation period has a greater impact on the current time to be adjusted. When Q is smaller, it often means that the total time length of the poor quality period in the current observation period is smaller, and it often means that the air quality in the current observation period is long-term stable at a good level, and the demand for air volume is smaller. Therefore, when Q is larger, it often means that the indoor environmental quality in the current observation period is poor, and it often means that the demand for air volume at the current time to be adjusted is greater.

[0156] Step S6, according to the overall air abnormality index corresponding to the current time to be adjusted, the air volume of the fan at the current time to be adjusted is adjusted and controlled.

[0157] As an example, the present step can include the following steps:

[0158] First, according to the overall air abnormality index corresponding to the current time to be adjusted, the fan air volume correction value corresponding to the current time to be adjusted is determined.

[0159] For example, the formula for determining the fan air volume correction value corresponding to the current time to be adjusted can be:

[0160] ;

[0161] Where f is the fan air volume correction value corresponding to the current time to be adjusted. ​is the minimum air volume that the fan can achieve during operation, which represents the lower limit of the fan's safe and stable operation. is a normalization function. Q is the overall air anomaly index corresponding to the current time to be adjusted. is the maximum air volume that the fan can achieve during operation, which represents the upper limit of the fan's capacity.

[0162] It should be noted that the larger Q is, the poorer the indoor environmental quality in the current observation period, and the greater the demand for air volume at the current time to be adjusted. Therefore, f can represent the required fan air volume at the current time to be adjusted.

[0163] Secondly, through the PID (Proportional Integral Derivative) controller, the fan air volume at the current time to be adjusted is adjusted to its corresponding fan air volume correction value.

[0164] It should be noted that the fan air volume correction value at the current time to be adjusted can be input into the PID controller to output a control signal, which will be used to adjust the speed or air volume of the fan. At this time, the fan will adjust its air volume in real time according to the signal output by the PID controller, so as to keep the indoor air quality within the required range.

[0165] Among them, PID control is a common feedback control algorithm, which adjusts the air volume in real time by monitoring air quality data (such as carbon dioxide concentration, PM2.5, etc.) to maintain the indoor air quality within the set required range.

[0166] Each environmental dimension data has its unique fluctuation rule and influencing factor. Simply analyzing the anomaly of a certain dimension may lead to a single system response. The embodiments of the present application can enhance the intelligence of the system by analyzing multiple dimensions of data, helping the system to understand the changes in the environment more comprehensively. Through intersection analysis, the system can make more reasonable control decisions according to the mutual relationship between different data, improving the accuracy and response speed of intelligent air volume adjustment of the fresh air system.

[0167] Reference Figure 2 Based on the same inventive concept as the above method embodiments, the present application provides an intelligent air volume control device for a fresh air system, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. The above computer program is executed by the processor to realize the steps of an intelligent air volume control method for a fresh air system, which can specifically include:

[0168] The dimension data acquisition module 201 is configured to acquire dimension data of each preset dimension collected at each time in the current observation period corresponding to the current time to be adjusted.

[0169] The screening and obtaining module 202 is configured to screen a target abnormal dimension corresponding to each time point from all preset dimensions according to the dimension data of the same preset dimension collected at different time points, and obtain a target abnormal time period of each time point in each target abnormal dimension corresponding thereto.

[0170] The indoor air deterioration degree determination module 203 is configured to determine a corresponding indoor air deterioration degree of each time point according to the dimension data in the target abnormal time period of each time point in the corresponding different target abnormal dimension.

[0171] The clustering and obtaining module 204 is configured to cluster different time points in a current observation time period according to the indoor air deterioration degrees of the different time points in the current observation time period, to obtain a target cluster, and obtain a target time period based on consecutive time points in each target cluster.

[0172] The overall air abnormality index determination module 205 is configured to determine an overall air abnormality index corresponding to a current to-be-adjusted time point according to all target abnormal dimensions and indoor air deterioration degrees of different time points in all target time periods.

[0173] The air volume adjustment control module 206 is configured to adjust and control the air volume of a fan at the current to-be-adjusted time point according to the overall air abnormality index corresponding to the current to-be-adjusted time point.

[0174] Figure 3 is a structural schematic diagram of a computer device provided by an embodiment of the present application. As shown in the example, Figure 3 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, wherein the processor 302 executes the computer program 303, so that the computer device can execute any of the air volume intelligent control methods of the fresh air system introduced above.

[0175] Based on the same inventive concept as the above method embodiments, the present application provides a server including a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes any of the air volume intelligent control methods of the fresh air system described above.

[0176] Based on the same inventive concept as the above method embodiments, the present application provides a computer program product, which includes computer program code. When the computer program code runs on a computer, it makes the computer execute any of the air volume intelligent control methods of the fresh air system described above.

[0177] 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.

[0178] 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.

[0179] 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. An air volume intelligent control method of a fresh air system, characterized in that, The method comprises the following steps: acquiring dimension data of each preset dimension collected at each time in a current observation period corresponding to a current time to be adjusted; screening target abnormal dimensions corresponding to each time from all preset dimensions according to dimension data of the same preset dimension collected at different times, and acquiring target abnormal periods of each time in each target abnormal dimension corresponding thereto; determining indoor air deterioration degrees corresponding to each time according to dimension data in target abnormal periods of each time in different target abnormal dimensions corresponding thereto; clustering different times in the current observation period according to indoor air deterioration degrees corresponding to different times in the current observation period, obtaining target clusters, and acquiring target periods based on continuous times in each target cluster; determining an overall air abnormality index corresponding to the current time to be adjusted according to all target abnormal dimensions and indoor air deterioration degrees corresponding to different times in all target periods; adjusting and controlling fan air volume at the current time to be adjusted according to the overall air abnormality index corresponding to the current time to be adjusted. The determination of the overall air abnormality index corresponding to the current time to be adjusted according to all target abnormal dimensions and indoor air deterioration degrees corresponding to different times in all target periods comprises: constructing a target abnormal dimension set corresponding to each time from all target abnormal dimensions corresponding to each time; segmenting each target period according to intersection conditions of target abnormal dimension sets corresponding to different times in each target period to obtain sub-periods; determining air abnormality complexity indexes corresponding to each target period according to lengths of different sub-periods in each target period and numbers of elements in intersections of target abnormal dimension sets corresponding to all times in each sub-period in each target period; determining air quality indexes corresponding to each target period according to air abnormality complexity indexes corresponding to each target period and mean values of indoor air deterioration degrees corresponding to all times in each target period; screening a target period corresponding to the smallest air quality index from all target periods as a reference period; if the air quality index corresponding to the target period is less than or equal to a preset quality threshold, determining the target period as a poor quality period; determining the overall air abnormality index corresponding to the current time to be adjusted according to an accumulated value of lengths of all poor quality periods, the air quality index corresponding to the reference period, and a length between an end time of the reference period and the current time to be adjusted.

2. The method of claim 1, wherein, The screening of target abnormal dimensions corresponding to each time from all preset dimensions according to dimension data of the same preset dimension collected at different times comprises: determining abnormal candidate times corresponding to each preset dimension according to dimension data of the same preset dimension collected at different times; screening target abnormal times corresponding to the preset dimension from all abnormal candidate times corresponding to each preset dimension; determining the preset dimension as a target abnormal dimension corresponding to each target abnormal time corresponding to the preset dimension.

3. The method of claim 2, wherein the method further comprises: The dimension data of the same preset dimension collected at different times is used to determine the abnormal candidate time corresponding to each preset dimension, including: An arbitrary time in the current observation period is determined as a marker time, and a time one hour before the marker time is determined as a reference time. An arbitrary preset dimension is determined as a marker dimension. If the difference between the dimension data of the marker dimension collected at the marker time and the dimension data of the marker dimension collected at the reference time is greater than a preset difference threshold, the marker time is determined as an abnormal candidate time corresponding to the marker dimension.

4. The method of claim 2, wherein the method further comprises: The target abnormal time corresponding to each preset dimension is selected from all abnormal candidate times corresponding to the preset dimension, including: An arbitrary preset dimension is determined as a marker dimension, and the continuous abnormal candidate times corresponding to the marker dimension form an abnormal candidate period corresponding to the marker dimension. The length of each abnormal candidate period corresponding to the marker dimension, and the maximum value and range of all dimension data of the marker dimension collected in each abnormal candidate period corresponding to the marker dimension are used to determine the air quality sudden change degree corresponding to each abnormal candidate period corresponding to the marker dimension. If the air quality sudden change degree corresponding to the abnormal candidate period corresponding to the marker dimension is greater than a preset quality sudden change threshold, each time in the abnormal candidate period is determined as a target abnormal time corresponding to the marker dimension.

5. The method of claim 2, wherein the method further comprises: The target abnormal period of each time in each target abnormal dimension corresponding to the time is obtained, including: An arbitrary time in the current observation period is determined as a marker time, and an arbitrary target abnormal dimension corresponding to the marker time is determined as a marker abnormal dimension. The target abnormal times corresponding to the marker abnormal dimension that are continuous with the marker time form a target abnormal period of the marker time in the marker abnormal dimension.

6. The method of claim 4, wherein the method further comprises: The indoor air deterioration degree corresponding to each time is determined according to the dimension data in the target abnormal period of each time in each different target abnormal dimension corresponding to the time, including: An arbitrary time in the current observation period is determined as a marker time. If the number of target abnormal dimensions corresponding to the marker time is 0, the indoor air deterioration degree corresponding to the marker time is set to a constant 0. If the number of target abnormal dimensions corresponding to the marker time is 1, the indoor air deterioration degree corresponding to the marker time is set to a constant 0.

1. If the number of target abnormal dimensions corresponding to the marked time point is greater than 1, then according to the correlation between the dimension data in the target abnormal period of the marked time point in different target abnormal dimensions corresponding to the marked time point, the change influence degree of the marked time point in each target abnormal dimension corresponding to the marked time point is determined, and based on the change influence degree of the marked time point in different target abnormal dimensions corresponding to the marked time point, the air quality sudden change degree of the abnormal candidate period to which the marked time point belongs in all abnormal candidate periods corresponding to different target abnormal dimensions corresponding to the marked time point, and the number of target abnormal dimensions corresponding to the marked time point, the indoor air deterioration degree corresponding to the marked time point is determined.

7. The method of claim 6, wherein the method further comprises: The change influence degree of the marked time point in each target abnormal dimension corresponding to the marked time point is determined according to the correlation between the dimension data in the target abnormal period of the marked time point in different target abnormal dimensions corresponding to the marked time point, comprising: All dimension data in the target abnormal period of the marked time point in each target abnormal dimension corresponding to the marked time point is constructed into an initial abnormal data sequence of the marked time point in each target abnormal dimension corresponding to the marked time point. The initial abnormal data sequences of the marked time point in different target abnormal dimensions corresponding to the marked time point are interpolated to obtain target abnormal data sequences of the marked time point in different target abnormal dimensions corresponding to the marked time point, wherein the number of elements in different target abnormal data sequences is the same. According to the number of elements in the initial abnormal data sequences of the marked time point in each two target abnormal dimensions corresponding to the marked time point, and the Pearson correlation coefficient between the target abnormal data sequences of the marked time point in each two target abnormal dimensions corresponding to the marked time point, the simultaneous change degree between each two target abnormal dimensions corresponding to the marked time point is determined. The average of the simultaneous change degree between each target abnormal dimension corresponding to the marked time point and all other target abnormal dimensions is determined as the change influence degree of the marked time point in each target abnormal dimension corresponding to the marked time point.

8. The method of claim 1, wherein, The target time period is segmented to obtain a sub-period according to the intersection of the target abnormal dimension sets corresponding to different time points in each target time period, comprising: If the intersection between the target abnormal dimension sets corresponding to two adjacent time points is empty, then the later time point of the two time points is determined as a temporary time point; Each target time period is segmented to obtain a sub-period by taking the temporary time point in each target time period as a segmentation point.

9. An air volume intelligent control device of a fresh air system, characterized in that, The processor is configured to execute the instructions stored in the memory to implement the method for intelligent control of air volume of a fresh air system according to any one of claims 1-8.

Images