CN110017567B - Anti-condensation control method and device - Google Patents
Anti-condensation control method and device Download PDFInfo
- Publication number
- CN110017567B CN110017567B CN201910094295.6A CN201910094295A CN110017567B CN 110017567 B CN110017567 B CN 110017567B CN 201910094295 A CN201910094295 A CN 201910094295A CN 110017567 B CN110017567 B CN 110017567B
- Authority
- CN
- China
- Prior art keywords
- behavior
- data set
- slope
- preset
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/41—Defrosting; Preventing freezing
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
Abstract
The invention provides an anti-condensation control method, which comprises the following steps: acquiring a real-time humidity data set; performing slope variance processing on the real-time humidity data set to extract target behavior characteristics; inputting the target behavior characteristics into a preset behavior characteristic library, and calculating the class probability of the target behavior characteristics belonging to preset behavior characteristics; and when the target behavior characteristic is a behavior characteristic of a user to be controlled, controlling to close the radiation cold source, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic. The invention triggers the anti-condensation measure based on the user behavior, and avoids the problem of poor condensation weakening effect of the traditional control mode.
Description
Technical Field
The invention relates to the field of air conditioning, in particular to an anti-condensation control method and device.
Background
With the improvement of living standard of people, air conditioning equipment is gradually widely used in various occasions. The condensation phenomenon during the operation of the air conditioner also attracts the attention of manufacturers, users and the like. Especially in summer cooling, when the temperature of the radiation surface is lowered below the dew point temperature, the surface condensation phenomenon of the wall or other equipment facilities is more prominent.
At present, in order to reduce the damage of the condensation phenomenon to the electrical equipment and other facilities, an indoor temperature controller is generally used for monitoring humidity, under the condition that the indoor radiation temperature is not changed and the atmospheric pressure is not changed, the dew point temperature T1 is increased when the humidity is increased, once the dew point temperature T1 is known to be greater than or equal to the radiation surface temperature T2 at time T, a radiation surface cold source is cut off (for example, a radiation surface water path is closed), refrigeration is suspended, so that the radiation surface temperature moves towards the direction far away from the dew point temperature, the indoor radiation surface temperature is forced to be increased to be greater than the dew point temperature after time delta T, and the condensation risk and the loss thereof are reduced.
However, in the existing measures for alleviating condensation, the cold source of the radiation surface is triggered to be cut off when the temperature condition reaches the condensation condition, so that even if the cold source is cut off, the response of the system and the temperature rise of the indoor radiation surface both need a certain time, the risk of condensation cannot be effectively weakened, and the condensation phenomenon is still easily generated.
Disclosure of Invention
The invention provides an anti-condensation control method and device, and aims to solve the problem that the effect of weakening condensation phenomenon is poor in the prior art.
In order to solve the technical problem, the invention is realized as follows:
an anti-condensation control method, the method comprising:
acquiring a real-time humidity data set;
performing slope variance processing on the real-time humidity data set to extract target behavior characteristics;
inputting the target behavior characteristics into a preset behavior characteristic library, and calculating the class probability of the target behavior characteristics belonging to preset behavior characteristics;
and when the target behavior characteristic is a behavior characteristic of a user to be controlled, controlling to close the radiation cold source, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic.
Optionally, the performing slope variance processing on the real-time humidity data set to extract target behavior features includes:
drawing a relation curve of humidity along with time change according to the real-time humidity data set;
calculating the slope of each data point of the real-time humidity data set in the relationship curve;
calculating the square of the slope of each data point according to the slope;
accumulating the slope square sliding preset item number to obtain a slope square accumulated sum;
and screening the data with the slope square accumulated sum larger than a preset threshold value to form a target behavior data set, wherein the target behavior data set represents the target behavior characteristics.
Optionally, before the acquiring the real-time humidity data set, the method further includes:
acquiring a historical humidity data set;
training the historical humidity data set through behavior feature analysis, and establishing a preset behavior feature library, wherein the preset behavior feature library comprises a plurality of different user behaviors, and the user behaviors are behaviors causing indoor humidity change.
Optionally, the training the historical humidity data set through behavior feature analysis, and the establishing a preset behavior feature library includes:
performing the slope variance processing on the historical humidity data set to generate a historical behavior data set;
performing clustering division on the historical behavior data set to generate each data cluster, wherein each data cluster represents different user behaviors;
and adding behavior labels to the data clusters to establish a preset behavior feature library.
The invention also provides an anti-condensation control device, which comprises:
the real-time data acquisition module is used for acquiring a real-time humidity data set;
the extraction module is used for executing slope variance processing on the real-time humidity data set to extract target behavior characteristics;
the calculation module is used for inputting the behavior characteristics into a preset behavior characteristic library and calculating the class probability that the target behavior characteristics belong to preset behavior characteristics;
and the control module is used for controlling to close the radiation cold source when the target behavior characteristic is a behavior characteristic of a user to be controlled, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic.
Optionally, the extracting module includes:
the drawing submodule is used for drawing a relation curve of humidity changing along with time according to the real-time humidity data set;
a slope calculation submodule for calculating the slope of each data point of the real-time humidity data set in the relationship curve;
the slope square calculation submodule is used for calculating the slope square of each data point according to the slope;
the accumulation submodule is used for accumulating the slope square sliding preset item number to obtain a slope square accumulation sum;
and the screening submodule is used for screening the data with the slope square accumulated sum larger than a preset threshold value to form a target behavior data set, wherein the target behavior data set represents the target behavior characteristics.
Optionally, the apparatus further comprises:
the historical data acquisition module is used for acquiring a historical humidity data set;
and the training module is used for training the historical humidity data set through behavior characteristic analysis and establishing a preset behavior characteristic library, wherein the preset behavior characteristic library comprises a plurality of different user behaviors, and the user behaviors are behaviors causing indoor humidity change.
Optionally, the training module includes:
a data set generation submodule for performing the slope variance processing on the historical humidity data set to generate a historical behavior data set;
the data cluster generation submodule is used for performing clustering division on the historical behavior data set to generate each data cluster, and each data cluster represents different user behaviors;
and the establishing submodule is used for adding behavior tags to each data cluster and establishing a preset behavior feature library.
Optionally, the apparatus further comprises:
compared with the prior art, the invention has at least the following advantages:
according to the anti-condensation control method and device provided by the invention, the target behavior characteristics in the real-time humidity data set are extracted through slope variance processing, the target behavior characteristics are input into the preset behavior characteristic library, the class probability that the target behavior characteristics belong to the preset behavior characteristics can be obtained, and therefore the user behavior represented by the real-time humidity data set is obtained.
Drawings
FIG. 1 is a flow chart of a condensation prevention control method provided by an embodiment of the invention;
FIG. 2 is a flow chart of another anti-condensation control method provided by the embodiment of the invention;
FIG. 3 is a graphical illustration of humidity versus time for an embodiment of the present invention;
FIG. 4 is a diagram illustrating the results of classification by the k-means clustering algorithm according to an embodiment of the present invention;
fig. 5 is a block diagram of an anti-condensation control device according to an embodiment of the present invention;
fig. 6 is a block diagram of a structure of another anti-condensation control device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An air conditioning control system according to the present invention will be described in detail by referring to several specific embodiments.
Example one
Referring to fig. 1, the present invention provides an anti-condensation control method, including:
Specifically, since the air conditioning equipment usually operates to heat or cool at a certain constant temperature, the radiation temperature is basically stable and does not change, and the atmospheric pressure in the room does not change, which causes the dew point temperature to increase when the humidity increases, relatively speaking, the difference between the radiation temperature and the dew point temperature is reduced, the two temperatures are closer to each other, and the condensation risk increases, so that the temperature controller in the equipment collects the humidity data in the room in real time as a real-time humidity data set, for example, the humidity data at intervals of 1 minute from 8 to 10 points is used as a real-time humidity data set, and the humidity data is used for predicting the user behavior to perform the condensation prevention control.
Specifically, the acquired real-time humidity data represents humidity data of a certain period of time, and user behaviors affecting humidity changes do not necessarily occur in the period of time, for example: between 8 o 'clock and 10 o' clock on the morning of the weekend, 8 o 'clock to 9 o' clock, the user is in the rest state, does not influence indoor humidity and changes, 9 o 'clock to 10 o' clock, and the user cleans the health after getting up, and long-time mopping action makes indoor humidity probably increase. Therefore, slope variance processing is performed on the real-time humidity data set, data can be screened and filtered, and target behavior characteristics implied by the data are extracted, wherein the target behavior characteristics represent that indoor humidity changes are influenced by user behaviors and condensation risks may be generated.
Specifically, based on the target behavior feature extracted from the real-time humidity data set, the target behavior feature may be input into a preset behavior feature library established in advance, and the target behavior feature is compared with various behaviors in the preset behavior feature library to determine the category probability that the target behavior feature belongs to the preset behavior feature. Such as: the behavior characteristics in the preset behavior characteristic library are A, B types, the target behavior characteristic M is the behavior characteristic to be determined, and M is obtained by calculation and is classified into AClass probability PAClass probability P that M belongs to BB. By PA、PBThe category with the higher category probability value may be considered as the category of the behavior feature to which the target behavior feature M belongs.
And 104, controlling to close the radiation cold source when the target behavior characteristic is a behavior characteristic of a user to be controlled, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic.
In particular, the specific category to which the target behavior characteristic represented by the real-time humidity data set belongs may be determined according to the aforementioned steps, however, not every type requires anti-condensation control, such as: the class A behavior characteristics represent user behaviors which have weak influence on indoor humidity, such as window opening behaviors in hot and humid days and the like, according to experimental monitoring, condensation risks of the user behaviors represented by the class A behavior characteristics are low, and condensation prevention control is not needed; the class B behavior characteristics represent user behaviors which have a serious influence on indoor humidity, for example, windowing behaviors in hot and humid days, boiling water, eating hot pot, mopping the floor and the like are monitored according to experiments, and the condensation risk of the user behaviors represented by the behavior characteristics is higher than that of the class A; obviously, when the behavior of the user is analyzed to belong to the class A behavior characteristics according to the target behavior characteristics M, the condensation risk does not exist basically, and the control of condensation prevention is performed without sacrificing the comfort of the user. For example, one situation that exists in practice may be the class probability P that M belongs to AA60%, class probability P that M belongs to BBIt can be determined that the target behavioral characteristics M belong to class a behavioral characteristics, and no anti-condensation control is required for user behaviors with low risk of condensation. Another situation that may exist in practice is the class probability P that M belongs to AA45%, class probability P that M belongs to BB55%, it can be determined that the target behavior feature M belongs to a class B behavior feature, that is, the user behavior represented by the current target behavior feature M belongs to a class B with a high condensation risk, and represents the user behavior with the high condensation risk, so that the anti-condensation control needs to be performed, and the closing of the spoke needs to be controlledThe cold source is penetrated to make indoor temperature rise, increases the difference of radiation temperature and dew point temperature, weakens the condensation phenomenon. Of course, it is also possible in practice for M to be assigned to class probability P of AA50%, class probability P of M being assigned to BBIn the scheme, the aim is to prevent condensation control, and for the condition that the probability is the same, the target behavior characteristic M is defaulted to be high-risk behavior characteristic of B-type behavior characteristic, and subsequent condensation prevention control is triggered to avoid condensation as much as possible. Thus, P in the above exampleA＞PBWhen P is not needed, there is no need for anti-condensation controlA≤PBAnd then, judging that the target behavior feature M is a B-type behavior feature, namely the behavior feature of the user to be controlled according to the class probability.
In summary, according to the anti-condensation control method provided by the invention, the target behavior feature in the real-time humidity data set is extracted through slope variance processing, the target behavior feature is input into the preset behavior feature library, and the class probability that the target behavior feature belongs to the preset behavior feature can be obtained, so that the user behavior represented by the real-time humidity data set is obtained, when the target behavior feature is the user behavior feature to be controlled, the risk of condensation generated by the user behavior can be considered to be high, the radiation cold source can be guided to be controlled to be turned off, so that the anti-condensation measure is triggered based on the user behavior, and the problem that the traditional control method has a poor condensation weakening effect is solved.
Example two
Referring to fig. 2, the present invention provides still another anti-condensation control method, including:
in step 201, a historical humidity data set is obtained.
Specifically, before humidity data are collected in real time, a large amount of historical humidity data with sufficient representativeness are collected and obtained in an experimental mode to form a historical humidity data set, wherein the sufficient representativeness means that the more the data quantity of the historical humidity data set is, the better the data quantity is, the longer the coverage time range is, the better the coverage time range is, the richer the behavior types of included users are, and therefore the historical data set can be analyzed and learned to construct a preset behavior feature library.
Specifically, since the acquired historical humidity data represents humidity data of a past experiment process for a certain period of time, user behaviors affecting humidity changes do not necessarily occur in the period of time, such as: between 8 o 'clock and 10 o' clock on the morning of the weekend, 8 o 'clock to 9 o' clock, the user is in the rest state, does not influence indoor humidity and changes, 9 o 'clock to 10 o' clock, and the user cleans the health after getting up, and long-time mopping action makes indoor humidity probably increase. Therefore, the historical humidity data set can be trained through behavior feature analysis, data with similar features are found out from a plurality of data, the data are classified, and a preset behavior feature library is established, wherein the preset behavior feature library comprises a plurality of different user behaviors, and the user behaviors are behaviors causing indoor humidity change, namely, each behavior feature represents different types of user behaviors.
Optionally, in another embodiment of the present invention, the step 202 may include sub-steps 2021 to 2023.
Substep 2021, performing the slope variance processing on the historical humidity data set generates a historical behavior data set.
Specifically, the historical humidity data set is the original data collected by the temperature controller, in order to ensure the representativeness of the sample, the number of the sample data is large, and the behavior of the user is not significant enough in the formed curve of the humidity changing along with time, as shown in fig. 3, the abscissa means the time of data collection, the ordinate means the humidity value, for convenience of illustration, the humidity value is converted, the data plotted on the ordinate is the relative humidity% RH, one decimal is reserved and then multiplied by 1000, and the curve a is the curve of the humidity changing along with time formed by the historical humidity data set. Data points with behavior characteristics can be amplified through slope variance processing, and the purpose is to extract the behavior characteristics from the historical humidity data set to generate a historical behavior data set, namely the historical behavior data set is a secondary data set formed by characteristic extraction of the historical humidity data set, as shown in fig. 3, and a curve b is a curve of humidity change with time formed by the historical behavior data set. The process of feature extraction by slope variance processing may refer to the following processes:
assume a raw historical humidity data set is humidity data collected at 1 minute intervals for 24 hours continuously over the course of the experiment.
First, the slope of each data point is calculated, and if the interval time difference is 1, the slope x (n) ═ y (n) — y (n-1), where n is 2, 3,4, … … 1440, x (1) ═ 0, n is the time of data acquisition, n is 2, 3,4, … …, i.e., the 2 nd minute, the 3 rd minute, the 4 th minute … …, y (n) indicates the humidity value corresponding to the time, i.e., y (2) indicates the humidity value at the 2 nd minute, y (3) indicates the humidity at the 3 rd minute, … ….
Next, the slope is squared to obtain the slope squared p (n) ═ x2(n)＝[y(n)-y(n-1)]2By square calculation, the data gap can be significantly increased, so that the behavior characteristics are shown.
Then, for each slope square data, sliding it four times in the historical time dimension direction, and accumulating the five slope square data to obtain a slope square sliding five-time accumulation sum a (n) -p (n-1) + p (n-2) + p (n-3) + p (n-4), wherein a (1) is 0, a (2) is 0, a (3) is 0, and a (4) is 0. And comparing the accumulated sum of the five data with a preset threshold, and sliding the slope square exceeding the threshold for five times to obtain the accumulated sum data as the data in the secondary data set, thereby realizing the extraction of the behavior characteristics.
It can be understood that the interval time of the acquired data and the number of slope square slips in the reference process of the slope variance processing for feature extraction are exemplary descriptions, and suitable parameters can be selected according to the scale of the sample size, the calculation efficiency and other factors.
Substep 2022, performing cluster partitioning on the historical behavior data set to generate data clusters, wherein the data clusters represent different user behaviors.
Specifically, the historical behavior data sets obtained by performing the slope variance processing on the features are data representing specific user behaviors, however, it is not known which data are similar, the historical behavior data sets can be clustered and divided by a k-means clustering algorithm common in the field of artificial intelligence to generate a plurality of data clusters, the number of the data clusters is the number of the classes, namely the number of the classes of the behavior features, and each data cluster represents different user behaviors. For example, fig. 4 shows a schematic diagram of the results classified by k-means clustering algorithm, the abscissa indicates humidity duration, the ordinate indicates humidity value, "·" in fig. 4 indicates Cluster 1, i.e., Cluster 1 in the legend, indicating user behavior with less influence on indoor humidity, and "a tangle-solidup" indicates Cluster 2, i.e., Cluster 2 in the legend, indicating user behavior with greater influence on indoor humidity, wherein "x" indicates the center point of each Cluster.
Substep 2023, adding a behavior tag to each data cluster, and establishing a preset behavior feature library.
Specifically, in order to distinguish different data clusters and facilitate management and analysis of data, a label may be added to the classified data clusters to indicate behavior characteristics, for example, the label Cluster 1 represents the Cluster 1 and represents a user behavior with a weak influence on indoor humidity, the label Cluster 2 represents the Cluster 2, a corresponding relationship between the data Cluster and the label is recorded in a preset behavior characteristic library representing the user behavior with a heavy influence on indoor humidity, that is, the data Cluster is determined, that is, which user behavior the data Cluster represents may be known.
Specifically, since the air conditioning equipment usually operates to heat or cool at a certain constant temperature, the radiation temperature is basically stable and does not change, and the atmospheric pressure in the room does not change, which causes the dew point temperature to increase when the humidity increases, relatively speaking, the difference between the radiation temperature and the dew point temperature is reduced, the two temperatures are closer to each other, and the condensation risk increases, so that the temperature controller in the equipment collects the humidity data in the room in real time as a real-time humidity data set, for example, the humidity data at intervals of 1 minute from 8 to 10 points is used as a real-time humidity data set, and the humidity data is used for predicting the user behavior to perform the condensation prevention control.
And step 204, drawing a relation curve of humidity along with time change according to the real-time humidity data set.
Specifically, for the acquired real-time humidity data set, the horizontal axis is time, and the vertical axis is humidity, and the approximate change situation of humidity can be visually displayed through a relation curve of humidity changing along with time, which is similar to the curve a shown in fig. 3.
Specifically, the slope of each data point of the real-time humidity data set may be calculated with reference to the slope calculation process described in sub-step 2021.
At step 206, the slope square of each data point is calculated according to the slope.
In particular, the slope square of each data point of the real-time humidity data set may be calculated with reference to the slope square calculation process described in sub-step 2021.
And step 207, accumulating the slope square sliding preset item number to obtain a slope square accumulated sum.
In particular, the slope squared cumulative sum for each data point of the real-time humidity data set may be calculated with reference to the slope squared cumulative sum calculation process described in sub-step 2021.
And 208, screening the data with the slope square accumulated sum larger than a preset threshold value to form a target behavior data set, wherein the target behavior data set represents the target behavior characteristics.
Specifically, the calculated multiple slope square accumulated sums may be compared with a preset threshold, and the slope square sliding accumulated sum data exceeding the threshold may be used as data in a target behavior data set, where the target behavior data set characterizes target behavior characteristics, so as to extract the behavior characteristics.
Specifically, the target behavior characteristics are input into the preset behavior characteristic library for a plurality of different user behaviors summarized and classified based on a large amount of historical data, that is, the target behavior data set is compared with each data cluster, and the class probability that the target behavior characteristics belong to the preset behavior characteristics is calculated by calculating the probability of which data cluster a specific data individual in the target behavior data set belongs to, so that the class of the target behavior characteristics is determined. For example, the category probability can be obtained by a logistic regression calculation, assuming that a certain data point of the target behavior data set is C, and the euclidean distances between the certain data point and the center points of the cluster 1 and the cluster 2 are X respectively1、X2Then the class probabilities of C belonging to cluster 1 and cluster 2 are P1＝X2/(X1+X2)、P2＝X1/(X1+X2). Thus, passing through P1、P2The data point C can be considered as belonging to the category with the higher probability value, and when the probabilities are the same, the data point C is classified as the category with the higher condensation risk by default.
And step 210, controlling to turn off a radiation cold source when the target behavior characteristic is a behavior characteristic of a user to be controlled, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic.
In particular, the specific category to which the target behavior characteristic represented by the real-time humidity data set belongs may be determined according to the aforementioned steps, however, not every type requires anti-condensation control, such as: the class A behavior characteristics represent user behaviors which have weak influence on indoor humidity, such as window opening behaviors in hot and humid days and the like, according to experimental monitoring, condensation risks of the user behaviors represented by the class A behavior characteristics are low, and condensation prevention control is not needed; the class B behavior characteristics represent user behaviors which have a serious influence on indoor humidity, such as window opening behaviors in hot and humid days, water boiling, chafing dish eating, mopping and the like, and according to experimental monitoring, the condensation risk of the user behaviors represented by the class B behavior characteristics is higher than that of the class A behavior; it is obvious thatWhen the behavior of the user is analyzed to belong to the A-class behavior characteristic according to the target behavior characteristic M, the condensation risk does not exist basically, and the condensation prevention control is performed without sacrificing the comfort of the user. For example, one situation that exists in practice may be the class probability P that M belongs to AA60%, class probability P that M belongs to BBAt 40%, it can be determined that the target behavior profile M belongs to a class a behavior profile, for which user behaviors with low risk of condensation do not require anti-condensation control. Another situation that may exist in practice is the class probability P that M belongs to AA45%, class probability P that M belongs to BB55%, it can be determined that the target behavior feature M belongs to a class B behavior feature, that is, the user behavior represented by the current target behavior feature M is determined from the class probability to belong to a class B with a high condensation risk, and represents the user behavior with the high condensation risk, so that condensation prevention control needs to be performed, a radiation cold source needs to be controlled to be turned off to raise the indoor temperature, the difference between the radiation temperature and the dew point temperature is increased, and the condensation phenomenon is weakened. Of course, it is also possible in practice for M to be assigned to class probability P of AA50%, class probability P of M being assigned to BBIn the scheme, the aim is to prevent condensation control, and for the condition that the probability is the same, the target behavior characteristic M is defaulted to be high-risk behavior characteristic of B-type behavior characteristic, and subsequent condensation prevention control is triggered to avoid condensation as much as possible. Thus, P in the above exampleA＞PBWhen P is not needed, there is no need for anti-condensation controlA≤PBAnd then, judging that the target behavior feature M is a B-type behavior feature, namely the behavior feature of the user to be controlled according to the class probability.
In summary, the anti-condensation control method provided by the invention performs clustering analysis on historical humidity data based on artificial intelligence clustering algorithm, finds out similar rules among the data, analyzes to form different user behavior categories to establish a preset behavior feature library, extracting target behavior characteristics from the real-time humidity data set through slope variance processing, inputting the target behavior characteristics into a preset behavior characteristic library to obtain the class probability that the target behavior characteristics belong to the preset behavior characteristics, thereby knowing the user behavior represented by the real-time humidity data set, when the target behavior characteristic is the behavior characteristic of the user to be controlled, the risk of condensation generated by the user behavior is considered to be higher, the control of closing the radiation cold source can be guided, therefore, the method and the device trigger the anti-condensation measure based on the user behavior, and avoid the problem that the traditional control mode has poor attenuation effect on the condensation phenomenon.
EXAMPLE III
Referring to fig. 5, the present invention provides an anti-condensation control apparatus, the apparatus including:
a real-time data acquiring module 501, configured to acquire a real-time humidity data set.
An extracting module 502, configured to perform slope variance processing on the real-time humidity data set to extract a target behavior feature.
A calculating module 503, configured to input the behavior feature into a preset behavior feature library, and calculate a category probability that the target behavior feature belongs to a preset behavior feature.
And a control module 504, configured to control to turn off the radiation cold source when the target behavior feature is a to-be-controlled user behavior feature, where the to-be-controlled user behavior feature is a behavior feature with a high condensation risk represented in the preset behavior feature.
In summary, according to the anti-condensation control method provided by the invention, the target behavior feature in the real-time humidity data set is extracted through slope variance processing, the target behavior feature is input into the preset behavior feature library, and the class probability that the target behavior feature belongs to the preset behavior feature can be obtained, so that the user behavior represented by the real-time humidity data set is obtained, when the target behavior feature is the user behavior feature to be controlled, the risk of condensation generated by the user behavior can be considered to be high, the radiation cold source can be guided to be controlled to be turned off, so that the anti-condensation measure is triggered based on the user behavior, and the problem that the traditional control method has a poor condensation weakening effect is solved.
Example four
Referring to fig. 6, the present invention provides an anti-condensation control apparatus, including:
a historical data obtaining module 601, configured to obtain a historical humidity data set.
A training module 602, configured to train the historical humidity data set through behavior feature analysis, and establish a preset behavior feature library, where the preset behavior feature library includes multiple different user behaviors, and the user behavior is a behavior that causes indoor humidity change.
The training module 602 includes:
a data set generation submodule 6021 operable to perform the slope variance processing on the historical humidity data set to generate a historical behavior data set.
A data cluster generation submodule 6022, configured to perform cluster division on the historical behavior data set to generate each data cluster, where each data cluster represents a different user behavior.
The establishing submodule 6023 is configured to add a behavior tag to each data cluster to establish a preset behavior feature library.
A real-time data acquisition module 603 configured to acquire a real-time humidity data set.
An extracting module 604, configured to perform slope variance processing on the real-time humidity data set to extract a target behavior feature.
The extraction module 604 includes:
a drawing submodule 6041 for drawing a relation curve of humidity changing with time according to the real-time humidity data set;
a slope calculation submodule 6042 configured to calculate a slope of each data point of the real-time humidity data set in the relationship curve;
a slope square calculation submodule 6043, configured to calculate a slope square of each data point according to the slope;
an accumulation submodule 6044 configured to accumulate the slope square sliding preset term number to obtain a slope square accumulation sum;
and a screening submodule 6045, configured to screen data in which the slope square cumulative sum is greater than a preset threshold to form a target behavior data set, where the target behavior data set represents the target behavior feature.
A calculating module 605, configured to input the target behavior feature into a preset behavior feature library, and calculate a category probability that the target behavior feature belongs to a preset behavior feature;
and the control module 606 is configured to control to turn off the radiation cold source when the target behavior feature is a to-be-controlled user behavior feature, where the to-be-controlled user behavior feature is a behavior feature with a high condensation risk represented in the preset behavior feature. In summary, the anti-condensation control method provided by the invention performs clustering analysis on historical humidity data based on artificial intelligence clustering algorithm, finds out similar rules among the data, analyzes to form different user behavior categories to establish a preset behavior feature library, extracting target behavior characteristics from the real-time humidity data set through slope variance processing, inputting the target behavior characteristics into a preset behavior characteristic library to obtain the class probability that the target behavior characteristics belong to the preset behavior characteristics, thereby knowing the user behavior represented by the real-time humidity data set, when the target behavior characteristic is the behavior characteristic of the user to be controlled, the risk of condensation generated by the user behavior is considered to be higher, the control of closing the radiation cold source can be guided, therefore, the method and the device trigger the anti-condensation measure based on the user behavior, and avoid the problem that the traditional control mode has poor attenuation effect on the condensation phenomenon.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the anti-condensation control apparatus described above may refer to the corresponding process in the embodiment of the anti-condensation control method, and will not be described herein again.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. An anti-condensation control method, characterized in that the method comprises:
acquiring a real-time humidity data set;
executing slope variance processing on the real-time humidity data set to extract target behavior characteristics, wherein the target behavior characteristics are behavior characteristics with condensation risks;
inputting the target behavior characteristics into a preset behavior characteristic library, and calculating the class probability of the target behavior characteristics belonging to preset behavior characteristics;
when the target behavior feature is a behavior feature of a user to be controlled, controlling to turn off a radiation cold source, wherein the behavior feature of the user to be controlled is a behavior feature with high condensation risk represented in the preset behavior feature;
the performing slope variance processing on the real-time humidity data set to extract target behavior features comprises:
drawing a relation curve of humidity along with time change according to the real-time humidity data set;
calculating the slope of each data point of the real-time humidity data set in the relationship curve;
calculating the square of the slope of each data point according to the slope;
accumulating the slope square sliding preset item number to obtain a slope square accumulated sum;
and screening the data with the slope square accumulated sum larger than a preset threshold value to form a target behavior data set, wherein the target behavior data set represents the target behavior characteristics.
2. The anti-condensation control method according to claim 1, further comprising, prior to said acquiring a real-time humidity data set:
acquiring a historical humidity data set;
training the historical humidity data set through behavior feature analysis, and establishing a preset behavior feature library, wherein the preset behavior feature library comprises a plurality of different user behaviors, and the user behaviors are behaviors causing indoor humidity change.
3. The anti-condensation control method according to claim 2, wherein the training of the historical humidity data set through behavior feature analysis, and the establishing of a preset behavior feature library comprises:
performing the slope variance processing on the historical humidity data set to generate a historical behavior data set;
performing clustering division on the historical behavior data set to generate each data cluster, wherein each data cluster represents different user behaviors;
and adding behavior labels to the data clusters to establish a preset behavior feature library.
4. An anti-condensation control device, characterized in that the device comprises:
the real-time data acquisition module is used for acquiring a real-time humidity data set;
the extraction module is used for executing slope variance processing on the real-time humidity data set to extract target behavior characteristics, wherein the target behavior characteristics are behavior characteristics with condensation risks;
the calculation module is used for inputting the target behavior characteristics into a preset behavior characteristic library and calculating the class probability that the target behavior characteristics belong to the preset behavior characteristics;
the control module is used for controlling to close the radiation cold source when the target behavior characteristic is a behavior characteristic of a user to be controlled, wherein the behavior characteristic of the user to be controlled is a behavior characteristic with high condensation risk represented in the preset behavior characteristic;
the extraction module comprises:
the drawing submodule is used for drawing a relation curve of humidity changing along with time according to the real-time humidity data set;
a slope calculation submodule for calculating the slope of each data point of the real-time humidity data set in the relationship curve;
the slope square calculation submodule is used for calculating the slope square of each data point according to the slope;
the accumulation submodule is used for accumulating the slope square sliding preset item number to obtain a slope square accumulation sum;
and the screening submodule is used for screening the data with the slope square accumulated sum larger than a preset threshold value to form a target behavior data set, wherein the target behavior data set represents the target behavior characteristics.
5. The anti-condensation control apparatus according to claim 4, further comprising:
the historical data acquisition module is used for acquiring a historical humidity data set;
and the training module is used for training the historical humidity data set through behavior characteristic analysis and establishing a preset behavior characteristic library, wherein the preset behavior characteristic library comprises a plurality of different user behaviors, and the user behaviors are behaviors causing indoor humidity change.
6. The anti-condensation control apparatus according to claim 5, wherein the training module comprises:
a data set generation submodule for performing the slope variance processing on the historical humidity data set to generate a historical behavior data set;
the data cluster generation submodule is used for performing clustering division on the historical behavior data set to generate each data cluster, and each data cluster represents different user behaviors;
and the establishing submodule is used for adding behavior tags to each data cluster and establishing a preset behavior feature library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094295.6A CN110017567B (en) | 2019-01-30 | 2019-01-30 | Anti-condensation control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094295.6A CN110017567B (en) | 2019-01-30 | 2019-01-30 | Anti-condensation control method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110017567A CN110017567A (en) | 2019-07-16 |
| CN110017567B true CN110017567B (en) | 2021-03-02 |
Family
ID=67188953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910094295.6A Expired - Fee Related CN110017567B (en) | 2019-01-30 | 2019-01-30 | Anti-condensation control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110017567B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102283283A (en) * | 2011-05-30 | 2011-12-21 | 广西大学 | Intelligentized superficial geothermal energy low-temperature grain storage system |
| CN102721117A (en) * | 2012-07-09 | 2012-10-10 | 广西电力工业勘察设计研究院 | Special air conditioner and dehumidifier for variable-air supply dew-point temperature-controlled hydropower station, and control method |
| JP2013047583A (en) * | 2011-08-29 | 2013-03-07 | Mitsubishi Electric Corp | Air conditioner |
| CN104076850A (en) * | 2014-07-21 | 2014-10-01 | 国家电网公司 | Method for achieving load switching based on single temperature and humidity sensor in control cubicle |
| CN106765744A (en) * | 2016-11-28 | 2017-05-31 | 天津商业大学 | It is determined that the method that radiation cooling system radiant panel surface temperature changes when lowering the temperature that supplies water |
| CN108917089A (en) * | 2018-04-18 | 2018-11-30 | 青岛海尔空调器有限总公司 | A kind of anti-condensation air conditioning control method and device |
-
2019
- 2019-01-30 CN CN201910094295.6A patent/CN110017567B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102283283A (en) * | 2011-05-30 | 2011-12-21 | 广西大学 | Intelligentized superficial geothermal energy low-temperature grain storage system |
| JP2013047583A (en) * | 2011-08-29 | 2013-03-07 | Mitsubishi Electric Corp | Air conditioner |
| CN102721117A (en) * | 2012-07-09 | 2012-10-10 | 广西电力工业勘察设计研究院 | Special air conditioner and dehumidifier for variable-air supply dew-point temperature-controlled hydropower station, and control method |
| CN104076850A (en) * | 2014-07-21 | 2014-10-01 | 国家电网公司 | Method for achieving load switching based on single temperature and humidity sensor in control cubicle |
| CN106765744A (en) * | 2016-11-28 | 2017-05-31 | 天津商业大学 | It is determined that the method that radiation cooling system radiant panel surface temperature changes when lowering the temperature that supplies water |
| CN108917089A (en) * | 2018-04-18 | 2018-11-30 | 青岛海尔空调器有限总公司 | A kind of anti-condensation air conditioning control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110017567A (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110263846B (en) | Fault diagnosis method based on fault data deep mining and learning | |
| KR101598979B1 (en) | Method and apparatus for estimating power consumption based on temperature | |
| US8078318B2 (en) | Appliance control apparatus and method | |
| CN107120794B (en) | Air conditioner operation condition adjusting method and air conditioner | |
| CN116610482B (en) | Intelligent monitoring method for operation state of electrical equipment | |
| CN111523397B (en) | Intelligent lamp post visual identification device, method and system and electronic equipment thereof | |
| JP2003256957A (en) | Device and system for detecting abnormality | |
| CN112283876A (en) | Air conditioner fault prediction method and air conditioner | |
| CN116304766A (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| CN110726233B (en) | Air conditioner control method, device, storage medium and memory | |
| CN114019847A (en) | Building group energy consumption abnormity management method and device | |
| CN115498313A (en) | Abnormity early warning method for air-cooled lithium ion battery energy storage container thermal management system | |
| CN110927217A (en) | Food freshness identification method based on electronic nose system and electronic nose system | |
| CN111080039A (en) | Fan cluster fault prediction method and system | |
| CN110017567B (en) | Anti-condensation control method and device | |
| CN116109011B (en) | Energy consumption management method and terminal for intelligent park | |
| CN116561535B (en) | Individualized building interaction design processing method | |
| CN102914328B (en) | Method for automatically regulating alarm thresholds of computer room temperature and humidity monitoring system | |
| CN111896831A (en) | Non-invasive comprehensive energy load monitoring method and system | |
| CN111339641A (en) | Refrigeration system management method and device, cloud platform and storage medium | |
| CN108375939A (en) | Environment control method and device and computer readable storage medium | |
| Haldi et al. | A comparison of alternative approaches for the modelling of window opening and closing behaviour | |
| CN115526275A (en) | Remote multi-source data monitoring and analyzing method and system for electricity safety | |
| CN110929800B (en) | Business body abnormal electricity utilization detection method based on sax algorithm | |
| CN110909813B (en) | Business abnormal electricity utilization detection method based on edge algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210302 Termination date: 20220130 |