CN116561535B - Individualized building interaction design processing method - Google Patents
Individualized building interaction design processing method Download PDFInfo
- Publication number
- CN116561535B CN116561535B CN202310840342.3A CN202310840342A CN116561535B CN 116561535 B CN116561535 B CN 116561535B CN 202310840342 A CN202310840342 A CN 202310840342A CN 116561535 B CN116561535 B CN 116561535B
- Authority
- CN
- China
- Prior art keywords
- data
- environment
- cluster
- environmental parameter
- building
- 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.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 42
- 238000013461 design Methods 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims abstract description 126
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 239000011159 matrix material Substances 0.000 claims abstract description 40
- 230000008859 change Effects 0.000 claims abstract description 24
- 230000035772 mutation Effects 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 98
- 230000008569 process Effects 0.000 claims description 48
- 230000014509 gene expression Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 22
- 238000007621 cluster analysis Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 abstract description 9
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 15
- 230000005856 abnormality Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 3
- KLARSDUHONHPRF-UHFFFAOYSA-N [Li].[Mn] Chemical compound [Li].[Mn] KLARSDUHONHPRF-UHFFFAOYSA-N 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Probability & Statistics with Applications (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to the field of data analysis, in particular to a personalized building interaction design processing method, which comprises the steps of obtaining each environment data matrix; calculating local change coefficients and mutation degrees of all data in an environment parameter matrix, further calculating noise factors of all the data, and obtaining a denoising model of all the data according to the noise factors of all the data; obtaining cluster radius setting factors under different cluster radii according to the relevance between the data in the clusters; taking the cluster radius corresponding to the maximum cluster radius setting factor as the optimal cluster radius of each data; obtaining the minimum inclusion point number of each data according to the optimal clustering radius of each data; a DBSCAN clustering algorithm is combined to obtain a plurality of clusters of each environmental parameter; and obtaining an abnormal value of the environmental parameter according to the clustering result of the environmental parameter, monitoring the indoor environment of the building, and adjusting equipment corresponding to the abnormal indoor environmental parameter. Thereby realizing the suitability of the indoor environment of the building and realizing the personalized interactive design treatment of the building.
Description
Technical Field
The application relates to the field of data analysis, in particular to a personalized building interaction design processing method.
Background
The personalized building interaction is mainly used for carrying out auxiliary interaction on the personalized building process so as to ensure that the personalized building meets the satisfied requirement. Interactive designs are currently used in a number of fields: the interactive design is mainly used for defining the content and the structure of communication between two or more interactive individuals so as to mutually coordinate the two or more interactive individuals to realize the interaction effect which is expected to be achieved. The method has the advantages that health factors of indoor environments of buildings are improved, the method is an important initial target in the field of building interaction, the application of building interaction is mainly used for controlling building equipment, so that the indoor environments of the buildings are monitored and analyzed, the building interaction is completed, and the suitability of the indoor environments is guaranteed.
The traditional method has the advantages that the method is simple and convenient, but the solution for setting the fixed threshold value is insufficient when the method is deployed, the requirement for setting the threshold value is higher, the artificial setting of the threshold value has larger subjectivity and randomness, false alarm and missing alarm are easy to occur, the scene suitability is low, and the personalized building interactive design processing effect is poor.
Therefore, in order to realize efficient personalized building interaction design, the application provides a personalized building interaction design processing method, which is used for constructing an environment data matrix for indoor environment parameter data through a plurality of sensors in a building, analyzing the environment data matrix, extracting the characteristics of each data, detecting and analyzing abnormal data, realizing personalized building interaction design processing according to the extracted abnormal data, adjusting equipment related to abnormal parameters and ensuring the indoor environment suitability.
Disclosure of Invention
In order to solve the technical problems, the application provides a personalized building interaction design processing method to solve the existing problems.
The application discloses a personalized building interaction design processing method based on the following technical scheme:
the embodiment of the application provides a personalized building interaction design processing method, which comprises the following steps of:
acquiring building indoor environment parameter data according to various sensors to obtain an environment data matrix of each environment parameter;
obtaining local change coefficients of all the data according to the data distribution conditions in the local window range of all the data in the environment data matrix; obtaining the mutation degree of each data according to the time sequence characteristics of each data in the environment data matrix; obtaining noise factors of all the data according to local change coefficients and mutation degrees of all the data in the environment data matrix; obtaining a denoising model of each data according to the noise factors of each data in the environment data matrix;
clustering each data in an environment data matrix by a DBSCAN clustering algorithm, presetting a maximum value and a minimum value of a clustering radius, and obtaining a clustering radius setting factor under different clustering radii according to the relevance between the data in the clusters after clustering analysis; taking the cluster radius corresponding to the maximum cluster radius setting factor as the optimal cluster radius of each data; obtaining the minimum inclusion point number of each data according to the optimal clustering radius of each data; performing cluster analysis on the data in the environment data matrix by combining a DBSCAN clustering algorithm, the optimal cluster radius and the minimum inclusion point number of each data, and obtaining a plurality of cluster clusters of each environment parameter;
obtaining an environment parameter abnormal value according to the clustering result of the environment parameter, obtaining a building indoor environment monitoring result according to the environment parameter abnormal value, and adjusting the building indoor environment by combining the building indoor environment monitoring result.
Preferably, the environmental data matrix of each environmental parameter is obtained by collecting the indoor environmental parameter data of the building according to a plurality of sensors, and the expression is:
in the method, in the process of the application,for the data of the building indoor environment parameter p at the data acquisition time N, < >>An environmental data matrix with environmental parameters p, and N is data acquisition setTime of day.
Preferably, the local change coefficient of each data is obtained according to the data distribution condition in the local window range of each data in the environmental data matrix, and the expression is:
in the method, in the process of the application,for data->Local coefficient of variation of>For data->Data set within local window, +.>For data->Total number of data categories in local window, +.>For data->The number of data and data +.>The ratio of the total number of data in the partial window, ln () is a logarithmic function based on e, < ->As a function of the argument x +.>Respectively corresponding data of the environmental parameter p at the data acquisition time a and the data acquisition time b, and the data are +.>For data->Absolute value of difference between>Data difference cut-off distance, +.>To avoid parameters with denominator zero.
Preferably, the mutation degree of each data is obtained according to the time sequence characteristics of each data in the environmental data matrix, and the expression is:
in the method, in the process of the application,for data->Data set within local window, +.>Data->Data within the local window range, min () is the operation taking the minimum value, max () is the operation taking the maximum value, +.>For normalization operations, ++>For numbers of digitsAccording to->E is a natural constant.
Preferably, the noise factor of each data is obtained according to the local change coefficient and the mutation degree of each data in the environmental data matrix, and the expression is:
in the method, in the process of the application,for data->Noise factor of->For data->Is used to determine the local coefficient of variation of (c),for data->Is a mutation level of (a).
Preferably, the denoising model of each data is obtained according to the noise factor of each data in the environmental data matrix, and the expression is:
in the method, in the process of the application,for data->Data value corresponding to denoised +.>Is->Data volume within local window, +.>For data->Data set within local window, +.>For data->Data within a local window->Is the noise cutoff value of the environmental parameter p, +.>For data->Noise factor of->For data->Is a noise factor of (a) is provided.
Preferably, the cluster radius setting factors under different cluster radii are obtained according to the relevance between the data in the clusters after cluster analysis, specifically:
in the method, in the process of the application,is core data +.>Cluster radius setting factor corresponding to cluster of +.>To take the following measuresFor the cluster of core data +.>Is cluster->Data in extremely bad, ++>Is cluster->Data within.
Preferably, the minimum number of points included in each data is obtained according to the optimal cluster radius of each data, and the expression is:
in the method, in the process of the application,for data->Minimum inclusion points of->To round down the function ++>For data->Is used for the optimal cluster radius of the cluster.
Preferably, the obtaining the environmental parameter abnormal value according to the clustering result of the environmental parameter specifically includes:
for the environment parameters with only one cluster, the maximum value and the minimum value of the environment parameters are manually selected, and according to the maximum value and the minimum value of the environment parameters, the abnormal value of the environment parameters is represented as follows:
in the method, in the process of the application,for the presence of an outlier corresponding to the environmental parameter u of only one cluster, +.>For normalization operations, ++>To take maximum value operation +.>Is the data mean value of the environmental parameter u, +.>Is the minimum value of the environmental parameter u, +.>Is the maximum value of the environmental parameter u;
when the number of the clustered clusters corresponding to the clustered environment parameters is larger than 1, calculating the abnormal value of the environment parameters according to each clustered environment parameter, wherein the expression is as follows:
in the method, in the process of the application,for the abnormal value corresponding to the environmental parameter v with the cluster number greater than 1, ++>For normalization operations, ++>To take maximum value operation +.>To take the minimum operation, +.>Variance of data mean of each cluster for environmental parameter v +.>For the number of clusters of the environmental parameter v, +.>Core point data of cluster i, which is the environmental parameter v.
Preferably, the method obtains the indoor environment monitoring result of the building according to the abnormal value of the environment parameter, specifically includes: according to the abnormal degree of each environmental parameter, the indoor condition of the building environment is monitored, and for the environmental parameters with the abnormal degree higher than the abnormal threshold, an early warning prompt is sent, equipment with the abnormal environmental parameters is properly regulated and controlled according to the abnormal early warning result of the environmental parameters, so that the personalized building interaction processing process is realized.
The application has at least the following beneficial effects:
the application realizes the monitoring of the indoor environment condition of the building by analyzing the data of the indoor environment parameters of the building, thereby providing reference opinion for the personalized building interaction design processing, realizing the processing process of the personalized building interaction and ensuring the indoor environment suitability of the building. Firstly, local change coefficients of all environmental parameter data are obtained by combining data change conditions within the range of a local window of all environmental parameter data, mutation degrees of all the data are obtained according to time sequence characteristics of all the data, noise data in the environmental parameters are detected and identified by combining the local change coefficients and the mutation degrees of the data, and noise removal processing is carried out on all the data by data noise factors, so that the influence of noise in all the environmental parameter data is solved, the data purity is improved, and the processing effect of personalized building interactive design is ensured;
meanwhile, in order to realize accurate monitoring of indoor environmental conditions of a building, the application performs cluster analysis on all environmental parameter data by combining a self-adaptive optimization clustering algorithm, performs self-adaptive setting on the optimal cluster radius of all data by combining a cluster radius factor of the data, solves the problem of reduced cluster precision caused by the fact that the cluster radius is randomly set too large and too small, further performs self-adaptive setting on the minimum inclusion points of all data by combining the optimal cluster radius of the data, and solves the problems of misclassification and low classification precision of the data caused by poor minimum inclusion point setting. The method has higher personalized building interaction processing precision, and can realize accurate clustering of the data in the personalized building interaction process so as to ensure the personalized building interaction effect.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a personalized building interaction design processing method provided by the application.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following detailed description is given below of a personalized building interaction design processing method according to the application, which is based on specific implementation, structure, characteristics and effects thereof, with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme based on a personalized building interaction design processing method provided by the application with reference to the accompanying drawings.
The embodiment of the application provides a personalized building interaction design processing method.
Specifically, the following method for processing the design of the interaction of the building based on individuation is provided, please refer to fig. 1, the method comprises the following steps:
and S001, acquiring data of indoor environment parameters of the building by various sensors to obtain an environment data matrix of each environment parameter.
In the embodiment, the indoor environment parameter data of the building is mainly acquired through the indoor sensor, the indoor environment of the building is monitored, and then the personalized indoor interaction process of the building is realized. Firstly, a sensor related to environmental parameters is installed in a building room for collecting data of the environmental parameters, and it is to be noted that many parameters related to the building indoor environment are included, including but not limited to temperature and humidity, indoor illuminance, air quality, water, noise, ventilation, etc., and the data of the lithium-manganese battery production parameters are collected by the corresponding sensor to obtain the data of each environmental parameter. It should be noted that the sensor type and the location deployment implementation can select the setting by themselves. In order to avoid the power consumption in the data acquisition process of the sensor, and consider that the change of the data of each parameter in the lithium-manganese battery production process has certain continuity, the implementation sets a data acquisition time interval t, that is, data of each parameter is acquired once at every interval t, and the embodiment is set as follows: t=1, and the practitioner can set up by himself in other embodiments.
After acquiring the data of each parameter related to the indoor environment of the building, the embodiment constructs each environment data matrix according to the data of each environment parameter, and takes the environment parameter p as an example to obtain the environment data matrix of the environment parameter p, which specifically comprises:
in the method, in the process of the application,for the data of the building indoor environment parameter p at the data acquisition time N, < >>For the environment data matrix of the environment parameter p, N is the data collection aggregation time, which can be set by the implementer, and in this embodiment, n=500.
Repeating the method to obtain an environment data matrix of each building indoor environment parameter for monitoring and analyzing the building indoor environment condition;
so far, the data of each environmental parameter can be obtained through each data acquisition sensor, and the environmental data matrix of each environmental parameter in the building room can be obtained.
And step S002, processing the indoor environment parameter data of the building, detecting and analyzing the abnormality, and obtaining the abnormal value of each environment parameter.
And analyzing the acquired environment data matrix to detect and extract abnormal data, so that the indoor environment of the building is monitored, and the personalized building interaction treatment effect is ensured. For the environmental data matrix, the embodiment processes and performs anomaly detection analysis to extract anomaly data of environmental parameters, and the environmental data matrix processing and anomaly detection analysis process specifically includes:
when the sensor collects environmental parameter data, the unavoidable noise in the building room affects the data collection purity, and meanwhile, certain noise is generated when the sensor is operated, so that a large amount of noise point data exist in the collected environmental parameter data, and the detection of the indoor environmental condition of the building room and the personalized building interaction processing effect are affected. Therefore, in order to improve the monitoring precision of the indoor environment condition of the building and ensure the data purity, the embodiment takes the environmental parameter p of the environmental data matrix as an example to extract the noise data;
for each data in the environmental parameter p, the embodiment detects the data change condition in the local window range of each data according to the data in the local window range of each data to obtain the local change coefficient of each data, and the expression is as follows:
in the method, in the process of the application,for data->Local coefficient of variation of>For data->Data set within local window, +.>For data->Total number of data categories in local window, +.>For data->The number of data and data +.>Data summary within a local WindowThe ratio of numbers, ln () is a logarithmic function based on e, ++>As a function of the argument x +.>Respectively corresponding data of the environmental parameter p at the data acquisition time a and the data acquisition time b, and the data are +.>For data->Absolute value of difference between>Data difference cut-off distance, +.>The value of (a) can be set by the practitioner himself, and the embodiment is set as +.>，/>To avoid the parameter with zero denominator, the practitioner can set himself, this embodiment is set to +.>. It should be noted that, in the embodiment, the data types are the same data types with the same size;
the method is repeated, and the local change coefficient of each data in the environmental parameter p is obtained and used for monitoring the local change condition of each data. For local coefficient of variation expressions, moleculesThe larger the data distribution variation degree in the local window of the data is, the more inconsistent the data in the local window is, and the denominator isThe larger the data ∈>The higher the degree of similarity to the data contained within the local window. Therefore, the larger the local change coefficient is, the larger the data change degree in the range of the data local window is, and the higher the data difference degree in the range of the data local window is;
repeating the method to obtain the local change coefficient of each data of the environmental parameter p;
considering that noise data has isolation and abnormal data mostly presents continuity, in order to improve the extraction precision of the noise data in the environmental parameter data and prevent the noise data from affecting environmental condition monitoring, in this embodiment, mutation degrees of each data are obtained according to time sequence characteristics of each data, and each data mutation degree expression is as follows:
in the method, in the process of the application,for data->Data set within local window, +.>Data->Data within the local window range, min () is the operation taking the minimum value, max () is the operation taking the maximum value, +.>For normalization operations, ++>For data->E is a natural constant. The higher the mutation degree of the data, the greater the possibility that the data is noise;
repeating the method to obtain the mutation degree of each data of the environmental parameter p;
obtaining noise factors of all the data of the environmental parameters according to the local change coefficients and the mutation degree of the data of the environmental parameters, wherein the expression is as follows:
in the method, in the process of the application,for data->Noise factor of->For data->Is used to determine the local coefficient of variation of (c),for data->Is a mutation level of (a). The greater the noise factor, the higher the likelihood that the data is noise data;
repeating the method to obtain the noise factors of the data of the environmental parameter p, and detecting the noise data in the environmental parameter p;
obtaining a denoising model of each data of the environmental parameter according to the noise factor of each data of the environmental parameter, wherein the denoising model expression of each data of the environmental parameter is as follows:
in the method, in the process of the application,for data->Data value corresponding to denoised +.>Is->Data volume within local window, +.>For data->Data set within local window, +.>For data->Data within a local window->The noise cutoff value of the environmental parameter p can be set by the practitioner himself, in this embodiment is set to +.>，/>For data->Noise factor of->For data->Is a noise factor of (1);
it should be noted that, for the data with the noise factor higher than the noise cut-off value, in order to prevent the extreme situation that the data value after the data denoising cannot be calculated because the data with the noise factor smaller than the noise threshold value does not exist in the local window range of the data, the embodiment sets the extreme situation, and when the extreme situation occurs, the corresponding environmental parameter data is removed;
thus, the noise extraction and processing of the indoor environment parameter data of the building can be realized according to the method, the data purity is ensured, and the indoor environment condition monitoring precision of the building is improved.
Further, the data of the environmental parameter are classified so as to detect and extract an abnormal data cluster of the environmental parameter, and the environmental parameter p is taken as an example, and the data clustering process of the environmental parameter p is described in detail by adopting a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm in the embodiment. The DBSCAN clustering algorithm comprises two clustering parameter clustering radiuses and the minimum number in clusters, most of clustering parameters in the traditional DBSCAN clustering algorithm are set by human being at random, the subjectivity of the process is strong, the process is too random, the situation that a large amount of data is misclassified is caused, the data clustering precision is affected, and the clustering radiuses in the environment parameter data clustering process are adaptively regulated and controlled to optimize the clustering effect;
first, for the cluster radius in the DBSCAN clustering process, if the cluster radius is set to be too large or too small, the data is misclassified, so the embodiment sets the maximum value of the cluster radiusMinimum->Sequentially from->Performing cluster analysis on the data of the environment number p by combining a DBSCAN clustering algorithm, and obtaining a cluster radius setting factor according to the relevance between the data in the clusters after the cluster analysis:
in the method, in the process of the application,is core data +.>Cluster radius setting factor corresponding to cluster of +.>To take the following measuresFor the cluster of core data +.>Is cluster->The data in the cluster is extremely bad, i.e. the difference between the maximum and minimum of the data in the cluster,/-, is>Is cluster->Data within;
the larger the clustering radius setting factor is, the better the clustering effect corresponding to the environmental parameter data is, so that the r value corresponding to the maximum clustering radius setting factor of the data is used as the optimal clustering radius of the data in the embodiment;
after the optimal cluster radius of the data is obtained, in order to improve the clustering effect and avoid the influence of poor setting of the minimum inclusion points on the clustering effect of the environmental parameter data, therefore, in this embodiment, the minimum inclusion points corresponding to the data are adaptively set according to the optimal cluster radius of the data, if the optimal cluster radius corresponding to the data is larger, if the minimum inclusion points of the smaller data are set, the data of different types are easily misjudged as the same cluster, so that more data misclassification problems are caused, if the optimal cluster radius corresponding to the data is smaller and the minimum inclusion points of the data are set larger, each data is an independent type, the effect of data clustering cannot be realized, and a more extreme situation occurs, therefore, the embodiment sets the minimum inclusion points of the data in an adaptive manner, and the minimum inclusion expressions of the data are specifically as follows:
in the method, in the process of the application,for data->Minimum inclusion points of->To round down the function ++>For data->Is defined by the optimal cluster radius of the cluster;
repeating the method to obtain the clustering radius and the minimum inclusion point number of each data in the environmental parameter clustering process, and carrying out clustering analysis on the environmental parameter data by combining a DBSCAN clustering algorithm, wherein the specific clustering process is the prior known technology and is not in the protection scope of the embodiment, and detailed description is not made here;
repeating the method, carrying out cluster analysis on each environmental parameter, and obtaining a plurality of clusters corresponding to each environmental parameter;
according to a plurality of clusters corresponding to each environmental parameter, the embodiment monitors each environmental parameter in a building in an abnormal manner, specifically:
when the environmental parameter passes through only one cluster after the clustering process, the abnormal condition of the environmental parameter cannot be monitored according to the data difference condition among different clusters of the environmental parameter, so that for the environmental parameter with only one cluster, the embodiment manually acquires the normal data range of the environmental parameter and monitors the abnormal degree of the environmental parameter according to the normal data range of the environmental parameter, and the expression is as follows:
in the method, in the process of the application,for the presence of an outlier corresponding to the environmental parameter u of only one cluster, +.>For normalization operations, ++>To take maximum value operation +.>Is the data mean value of the environmental parameter u, +.>Is the minimum value in the environment parameter u, +.>Is the maximum value of the environmental parameter u. The greater the outlier, the more serious the abnormal condition of the corresponding environmental parameter;
when the number of the clusters corresponding to the clustered environment parameters is larger than 1, monitoring the abnormal condition of the environment parameters according to the clusters of the environment parameters to obtain the abnormal degree of the environment parameters, wherein the expression is as follows:
in the method, in the process of the application,for the abnormal value corresponding to the environmental parameter v with the cluster number greater than 1, ++>For normalization operations, ++>To take maximum value operation +.>To take the minimum operation, +.>Variance of data mean of each cluster for environmental parameter v +.>For the number of clusters of the environmental parameter v, +.>Core point data of cluster i, which is the environmental parameter v. Similarly, the greater the outlier, the more serious the abnormal condition of the corresponding environmental parameter, the greater the degree of abnormality;
the method is repeated to obtain the abnormal value of each environmental parameter in the building room, and the abnormal value is used for monitoring and analyzing the environmental condition in the building room.
And step S003, monitoring the indoor environment of the building is realized according to the abnormal values of the environmental parameters, and reliable basis is provided for interactive design of the building.
According to the abnormal degree of each environmental parameter, the indoor condition of the building environment is monitored, and for the environmental parameters with the abnormal degree higher than the abnormal threshold, an early warning prompt is sent, equipment with the abnormal environmental parameters is properly regulated and controlled according to the abnormal early warning result of the environmental parameters, so that the personalized building interaction processing process is realized. The specific regulation and control method implementation can be set by the user according to actual conditions, for example, when the air quality abnormality degree is higher than an abnormality threshold value, automatic windowing and ventilation are carried out to ensure that the indoor air of the building is clear; when the abnormality degree of the indoor illuminance is higher than the abnormality threshold, the indoor lighting device is automatically turned on to ensure the indoor environment brightness. The abnormality degree threshold value is set by the operator, and the present embodiment is set to 0.5.
In summary, the embodiment of the application realizes the monitoring of the indoor environment condition of the building by analyzing the data of each indoor environment parameter of the building, thereby providing reference opinion for the personalized building interaction design processing, realizing the processing process of the personalized building interaction and ensuring the indoor environment suitability of the building. Firstly, the embodiment of the application combines the data change condition in the local window range of each environmental parameter data to obtain the local change coefficient of each environmental parameter data, obtains the mutation degree of each data according to the time sequence characteristic of each data, combines the local change coefficient and the mutation degree of the data, detects and identifies the noise data in the environmental parameters, and carries out denoising treatment on each data through the data noise factor, thereby solving the influence of noise in each environmental parameter data, improving the data purity and ensuring the treatment effect of personalized building interactive design;
meanwhile, in order to accurately monitor the indoor environment condition of the building, the embodiment of the application performs cluster analysis on the environmental parameter data by combining the self-adaptive optimized clustering algorithm, performs self-adaptive setting on the optimal clustering radius of each data by combining the clustering radius factor of the data, solves the problem of reduced clustering precision caused by excessively large and excessively small random setting of the clustering radius, further performs self-adaptive setting on the minimum inclusion points of each data by combining the optimal clustering radius of the data, and solves the problems of misclassification and low classification precision of the data caused by poor setting of the minimum inclusion points. The embodiment of the application has higher personalized building interaction processing precision, and can realize accurate clustering of the data in the personalized building interaction process so as to ensure the personalized building interaction effect.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (5)
1. The personalized building interaction design processing method is characterized by comprising the following steps of:
acquiring building indoor environment parameter data according to various sensors to obtain an environment data matrix of each environment parameter;
obtaining local change coefficients of all the data according to the data distribution conditions in the local window range of all the data in the environment data matrix; obtaining the mutation degree of each data according to the time sequence characteristics of each data in the environment data matrix; obtaining noise factors of all the data according to local change coefficients and mutation degrees of all the data in the environment data matrix; obtaining a denoising model of each data according to the noise factors of each data in the environment data matrix;
clustering each data in an environment data matrix by a DBSCAN clustering algorithm, presetting a maximum value and a minimum value of a clustering radius, and obtaining a clustering radius setting factor under different clustering radii according to the relevance between the data in the clusters after clustering analysis; taking the cluster radius corresponding to the maximum cluster radius setting factor as the optimal cluster radius of each data; obtaining the minimum inclusion point number of each data according to the optimal clustering radius of each data; performing cluster analysis on the data in the environment data matrix by combining a DBSCAN clustering algorithm, the optimal cluster radius and the minimum inclusion point number of each data, and obtaining a plurality of cluster clusters of each environment parameter;
obtaining an environment parameter abnormal value according to the clustering result of the environment parameter, obtaining a building indoor environment monitoring result according to the environment parameter abnormal value, and adjusting the building indoor environment by combining the building indoor environment monitoring result;
the local change coefficient of each data is obtained according to the data distribution condition in the local window range of each data in the environment data matrix, and the expression is as follows:
in the method, in the process of the application,for data->Local coefficient of variation of>For data->Data set within local window, +.>For data->Total number of data categories in local window, +.>For data->The number of data and data +.>The ratio of the total number of data in the partial window, ln () is a logarithmic function based on e, < ->As a function of the argument x +.>Respectively corresponding data of the environmental parameter p at the data acquisition time a and the data acquisition time b, and the data are +.>For data->Absolute value of difference between>Data difference cut-off distance, +.>Parameters for avoiding zero denominator;
the mutation degree of each data is obtained according to the time sequence characteristics of each data in the environment data matrix, and the expression is as follows:
in the method, in the process of the application,for data->Data set within local window, +.>For data->Data within the local window range, min () is the operation taking the minimum value, max () is the operation taking the maximum value, +.>For normalization operations, ++>For data->E is a natural constant;
the noise factor of each data is obtained according to the local change coefficient and the mutation degree of each data in the environment data matrix, and the expression is as follows:
in the method, in the process of the application,for data->Noise factor of->For data->Is used to determine the local coefficient of variation of (c),for data->Is a mutation degree of (2);
the denoising model of each data is obtained according to the noise factors of each data in the environment data matrix, and the expression is as follows:
in the method, in the process of the application,for data->Data value corresponding to denoised +.>Is->The amount of data within the local window is,for data->Data set within local window, +.>For data->Data within a local window->Is the noise cutoff value of the environmental parameter p, +.>For data->Noise factor of->For data->Is a noise factor of (1);
the clustering result according to the environmental parameter obtains the environmental parameter abnormal value, specifically:
for the environment parameters with only one cluster, the maximum value and the minimum value of the environment parameters are manually selected, and according to the maximum value and the minimum value of the environment parameters, the abnormal value of the environment parameters is represented as follows:
in the method, in the process of the application,for the presence of an outlier corresponding to the environmental parameter u of only one cluster, +.>For the purpose of the normalization operation,to take maximum value operation +.>Is the data mean value of the environmental parameter u, +.>At the minimum value of the environmental parameter u,is the maximum value of the environmental parameter u;
when the number of the clustered clusters corresponding to the clustered environment parameters is larger than 1, calculating the abnormal value of the environment parameters according to each clustered environment parameter, wherein the expression is as follows:
in the method, in the process of the application,for the abnormal value corresponding to the environmental parameter v with the cluster number greater than 1, ++>For the purpose of the normalization operation,to take maximum value operation +.>To take the minimum operation, +.>Variance of data mean of each cluster for environmental parameter v +.>For the number of clusters of the environmental parameter v, +.>Core point data of cluster i, which is the environmental parameter v.
2. The method for processing the personalized building interaction design according to claim 1, wherein the environmental data matrix of each environmental parameter is obtained by collecting the indoor environmental parameter data of the building according to a plurality of sensors, and the expression is as follows:
in the method, in the process of the application,for the data of the building indoor environment parameter p at the data acquisition time N, < >>And N is the data acquisition aggregation time for the environmental data matrix of the environmental parameter p.
3. The method for processing the personalized building interaction design according to claim 1, wherein the cluster radius setting factors under different cluster radii are obtained according to the relevance between the data in the clusters after the cluster analysis, specifically:
in the method, in the process of the application,is core data +.>Cluster radius setting factor corresponding to cluster of +.>To->For the cluster of core data +.>Is cluster->Data in extremely bad, ++>Is cluster->Data within.
4. The personalized building interaction design processing method according to claim 1, wherein the minimum inclusion point number of each data is obtained according to the optimal clustering radius of each data, and the expression is:
in the method, in the process of the application,for data->Minimum inclusion points of->To round down the function ++>Is data ofIs used for the optimal cluster radius of the cluster.
5. The method for processing the personalized building interaction design according to claim 1, wherein the method for obtaining the building indoor environment monitoring result according to the environment parameter abnormal value is specifically as follows: according to the abnormal degree of each environmental parameter, the indoor condition of the building environment is monitored, and for the environmental parameters with the abnormal degree higher than the abnormal threshold, an early warning prompt is sent, equipment with the abnormal environmental parameters is properly regulated and controlled according to the abnormal early warning result of the environmental parameters, so that the personalized building interaction processing process is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310840342.3A CN116561535B (en) | 2023-07-11 | 2023-07-11 | Individualized building interaction design processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310840342.3A CN116561535B (en) | 2023-07-11 | 2023-07-11 | Individualized building interaction design processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116561535A CN116561535A (en) | 2023-08-08 |
| CN116561535B true CN116561535B (en) | 2023-09-19 |
Family
ID=87486568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310840342.3A Active CN116561535B (en) | 2023-07-11 | 2023-07-11 | Individualized building interaction design processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116561535B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975539B (en) * | 2023-08-16 | 2024-03-19 | 杭州火奴数据科技有限公司 | Marketing data storage management system based on clustering algorithm |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111329228A (en) * | 2020-03-05 | 2020-06-26 | 安徽建筑大学 | Creation office table with adjustable angle for art design |
| WO2021162481A1 (en) * | 2020-02-11 | 2021-08-19 | Samsung Electronics Co., Ltd. | Electronic device and control method thereof |
| CN114036605A (en) * | 2021-10-29 | 2022-02-11 | 河海大学 | Kalman filtering steel truss bridge structural parameter monitoring method based on adaptive control |
| CN114116829A (en) * | 2020-08-31 | 2022-03-01 | 中兴通讯股份有限公司 | Abnormal data analysis method, abnormal data analysis system, and storage medium |
| CN115392408A (en) * | 2022-10-31 | 2022-11-25 | 山东鲁抗医药集团赛特有限责任公司 | Method and system for detecting abnormal operation of electronic particle counter |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
| CN116237817A (en) * | 2023-05-06 | 2023-06-09 | 济南章力机械有限公司 | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things |
| CN116304766A (en) * | 2023-05-25 | 2023-06-23 | 山东艾迈科思电气有限公司 | Multi-sensor-based quick assessment method for state of switch cabinet |
| CN116319110A (en) * | 2023-05-24 | 2023-06-23 | 保定思齐智科信息科技有限公司 | Data acquisition and management method for industrial multi-source heterogeneous time sequence data |
| CN116343953A (en) * | 2023-05-30 | 2023-06-27 | 苏州绿华科技有限公司 | Intelligent community management system based on artificial intelligence |
| CN116404186A (en) * | 2023-06-08 | 2023-07-07 | 西安黄河电子技术有限公司 | Power lithium-manganese battery production system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11048727B2 (en) * | 2018-09-10 | 2021-06-29 | Ciena Corporation | Systems and methods for automated feature selection and pattern discovery of multi-variate time-series |
-
2023
- 2023-07-11 CN CN202310840342.3A patent/CN116561535B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021162481A1 (en) * | 2020-02-11 | 2021-08-19 | Samsung Electronics Co., Ltd. | Electronic device and control method thereof |
| CN111329228A (en) * | 2020-03-05 | 2020-06-26 | 安徽建筑大学 | Creation office table with adjustable angle for art design |
| CN114116829A (en) * | 2020-08-31 | 2022-03-01 | 中兴通讯股份有限公司 | Abnormal data analysis method, abnormal data analysis system, and storage medium |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN114036605A (en) * | 2021-10-29 | 2022-02-11 | 河海大学 | Kalman filtering steel truss bridge structural parameter monitoring method based on adaptive control |
| CN115392408A (en) * | 2022-10-31 | 2022-11-25 | 山东鲁抗医药集团赛特有限责任公司 | Method and system for detecting abnormal operation of electronic particle counter |
| CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
| CN116237817A (en) * | 2023-05-06 | 2023-06-09 | 济南章力机械有限公司 | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things |
| CN116319110A (en) * | 2023-05-24 | 2023-06-23 | 保定思齐智科信息科技有限公司 | Data acquisition and management method for industrial multi-source heterogeneous time sequence data |
| CN116304766A (en) * | 2023-05-25 | 2023-06-23 | 山东艾迈科思电气有限公司 | Multi-sensor-based quick assessment method for state of switch cabinet |
| CN116343953A (en) * | 2023-05-30 | 2023-06-27 | 苏州绿华科技有限公司 | Intelligent community management system based on artificial intelligence |
| CN116404186A (en) * | 2023-06-08 | 2023-07-07 | 西安黄河电子技术有限公司 | Power lithium-manganese battery production system |
Non-Patent Citations (4)
| Title |
|---|
| An enhanced principal component analysis method with Savitzky–Golay filter and clustering algorithm for sensor fault detection and diagnosis;Shuqing Wen 等;《Applied Energy》;第337卷;全文 * |
| Spatiotemporal correlation analysis of the dynamic response of supertall buildings under ambient wind conditions;Bin Yang 等;《The Structural Design of Tall and Special Buildings》;第31卷(第4期);全文 * |
| 一种三维激光点云中建筑物立面分割方法;李玉兵;《遥感信息》;第36卷(第2期);全文 * |
| 文化遗产的保护利用与地方特色文化产业融合发展路径研究;程颖 等;《合肥师范学院学报》;第40卷(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116561535A (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298487B (en) | Indoor temperature prediction method for meeting personalized demands of users | |
| CN116561535B (en) | Individualized building interaction design processing method | |
| CN116304766B (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| WO2019052241A1 (en) | Refrigerant leak detection method and device for air conditioner | |
| CN109873779B (en) | LSTM-based hierarchical wireless signal modulation type identification method | |
| CN117421618B (en) | Building energy consumption monitoring method and system | |
| CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
| CN116404186B (en) | Power lithium-manganese battery production system | |
| CN115696690B (en) | Distributed intelligent building illumination self-adaptive energy-saving control method | |
| CN114518143A (en) | Intelligent environment sensing system | |
| CN116649160B (en) | Edible fungus strain production monitoring system and monitoring method | |
| CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
| CN115035686A (en) | Real-time falling detection method, system and medium based on channel state information | |
| CN110555524A (en) | training sample data acquisition method and device based on indoor environment monitoring | |
| CN115659195A (en) | Online atmospheric pollution identification method | |
| CN117454201B (en) | Method and system for detecting abnormal operation state of smart power grid | |
| CN117708627A (en) | Intelligent dome adjusting method and system for all-sky-domain telescope | |
| CN117010638B (en) | Intelligent management method and system for hotel equipment | |
| CN117782198A (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN116432088A (en) | Intelligent monitoring method and system for layer thickness of composite optical film | |
| CN114283367B (en) | Artificial intelligent open fire detection method and system for garden fire early warning | |
| CN114489200A (en) | Warmhouse booth environmental control system | |
| CN110781538B (en) | Windowing simulation algorithm based on field monitoring | |
| CN117609929B (en) | Industrial production line fault online diagnosis method and system based on big data | |
| CN116738296B (en) | Comprehensive intelligent monitoring system for machine room conditions |
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 |