CN115577606B - Building indoor environment detection system and detection method - Google Patents

Building indoor environment detection system and detection method Download PDF

Info

Publication number
CN115577606B
CN115577606B CN202211576539.2A CN202211576539A CN115577606B CN 115577606 B CN115577606 B CN 115577606B CN 202211576539 A CN202211576539 A CN 202211576539A CN 115577606 B CN115577606 B CN 115577606B
Authority
CN
China
Prior art keywords
model
grid
indoor environment
sub
dimensional
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
Application number
CN202211576539.2A
Other languages
Chinese (zh)
Other versions
CN115577606A (en
Inventor
周宗强
周小霞
曹利剑
陈佳豪
白一阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Zhonghao Application Engineering Technology Research Institute Co ltd
Original Assignee
Zhejiang Zhonghao Application Engineering Technology Research Institute Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Zhonghao Application Engineering Technology Research Institute Co ltd filed Critical Zhejiang Zhonghao Application Engineering Technology Research Institute Co ltd
Priority to CN202211576539.2A priority Critical patent/CN115577606B/en
Publication of CN115577606A publication Critical patent/CN115577606A/en
Application granted granted Critical
Publication of CN115577606B publication Critical patent/CN115577606B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Fluid Mechanics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

The invention provides a building indoor environment detection system and a detection method, which belong to the technical field of processing and manufacturing energy consumption calculation processing, and are used for establishing a three-dimensional indoor environment model and dividing the established three-dimensional indoor environment model into grids; performing airflow modeling on the three-dimensional indoor environment model divided into the grids to form an airflow model; calculating a primitive value contributing to the variance of the air flow model in each unit mesh by discretizing the variance of the air flow model on the mesh, selecting a primitive value data point, and sub-meshing the mesh according to the primitive value data point; constructing a multi-model of the sub-grids, selecting P positions as energy nodes, obtaining attribute values of the P energy nodes to perform model reconstruction on each sub-grid, and calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of the plurality of sub-grids reconstructed by the attribute values of the P energy nodes in each sub-grid, thereby realizing accurate detection of the indoor environment of the building.

Description

Building indoor environment detection system and detection method
Technical Field
The invention relates to the field of building environment and building energy conservation, in particular to a system and a method for detecting indoor environment of a building.
Background
In recent years, the construction industry of China is rapidly developed, and the quality and the comfort level of the indoor environment gradually become a focus of people's attention. The comfortable indoor environment of the building is of great importance to building users, and the environmental comfort is an important aspect of embodying the green building quality.
The building system is a complex system and has the characteristics of nonlinearity, large hysteresis, multivariable, serious coupling, slow change and the like. The indoor temperature, pressure and flow rate at the next moment can be calculated by utilizing the characteristic of large hysteresis of a building system, so that the opening and closing of a building valve are guided, and the energy is saved while the thermal comfort of a user is ensured. However, in the heating period, the indoor temperature of the building is affected by various nonlinear factors such as outdoor meteorological factors and historical temperature, so that the mechanism modeling of the indoor temperature, pressure and flow speed of the building is complicated and difficult.
The simulation method based on the physical model can effectively reflect the mechanism relation of the indoor temperature, the pressure and the flow velocity of the building, but the accuracy of the model is poor due to inaccurate measured data and high complexity of the physical model. The method for training and calibrating the environmental model of the building by using the historical data and the weather data of the building is very sensitive to the sample size, and the requirement of a training data set is very large. Therefore, the existing analysis method based on building indoor environment detection cannot completely meet the requirement of multivariate data, and an analysis method with high model precision, fast response on the demand side and high detection precision is urgently needed.
Disclosure of Invention
In order to solve the technical problem, the invention provides a method for detecting the indoor environment of a building, which comprises the following steps:
s1, establishing a three-dimensional indoor environment model, and dividing the established three-dimensional indoor environment model into grids;
s2, performing air flow modeling on the three-dimensional indoor environment model divided into grids to form an air flow model;
s3, discretizing variables of the airflow model on grids, calculating element values contributing to the variables of the airflow model in each unit grid, selecting element value data points, and sub-grid dividing the grids according to the element value data points;
s4, constructing multiple models of the sub-grids, selecting P positions as energy nodes, and obtaining attribute values of the P energy nodes to perform model reconstruction on each sub-grid;
and S5, calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of the multiple sub-grids reconstructed by the attribute values of the p energy nodes in each sub-grid.
Further, step S4 includes the steps of:
s41, in an air flow field H with sub-grids of n-dimensional unit grids, n element values respectively corresponding to each unit grid form a group of element value data sets, wherein the element values corresponding to m-dimensional unit grids form element value data subsets, and the optimal element value data subsets are searched
Figure 439358DEST_PATH_IMAGE001
Such that primitive value data sets on the air flow field H of the submesh
Figure 763023DEST_PATH_IMAGE002
To the primitive value data subsets
Figure 73919DEST_PATH_IMAGE001
Maximum projection of (d):
Figure 875653DEST_PATH_IMAGE003
（1）；
in the formula (I), the compound is shown in the specification,
Figure 955604DEST_PATH_IMAGE004
，
Figure 43646DEST_PATH_IMAGE005
is the energy norm of the air flow field H,
Figure 717204DEST_PATH_IMAGE006
is a desired operator;
s42, primitive values on air flow field H of sub-grid at any time t
Figure 181683DEST_PATH_IMAGE007
Average velocity field from multiple cell grids
Figure 116141DEST_PATH_IMAGE008
Pressure field
Figure 516029DEST_PATH_IMAGE009
And temperature field
Figure 535938DEST_PATH_IMAGE010
Is expressed by the sum of (1) as shown in formula (2):
Figure 538529DEST_PATH_IMAGE011
(2)；
converting formula (1) into a characteristic value problem, as shown in formula (3):
Figure 468439DEST_PATH_IMAGE012
(3)；
in the formula (I), the compound is shown in the specification,
Figure 163863DEST_PATH_IMAGE013
is the product of the standard tensor in the form of,
Figure 671067DEST_PATH_IMAGE014
is composed of
Figure 352715DEST_PATH_IMAGE015
Dual element value of (2), solved for
Figure 261766DEST_PATH_IMAGE016
The number of which constitutes a plurality of patterns of the sub-grid,
Figure 862511DEST_PATH_IMAGE017
is the corresponding characteristic value;
s43, for the m obtained modes, arranging a data acquisition module at a unit grid position corresponding to P positions with the maximum element value absolute value of each mode, and calculating the m-dimensional element value data according to a formula (2) by using speed values, pressure values and temperature values acquired from the P positions;
s44, selecting the p positions as energy nodes, taking the temperature, the speed and the pressure as attribute values of the energy nodes, and realizing real-time reconstruction of the air flow field of the sub-grid through the attribute values of the p energy nodes.
Further, in step S44, p energy nodes, the modulus coefficient b of the air flow field of the sub-grid at any time k Is estimated value of
Figure 732378DEST_PATH_IMAGE018
Estimating the components of the attribute of the energy nodes acquired by the P energy nodes in real time:
Figure 342351DEST_PATH_IMAGE019
(4)；
wherein the content of the first and second substances,
Figure 105908DEST_PATH_IMAGE020
for the ith energy node at the time t, the coordinate is x i The component of the property value at (c).
Further, in step S43, the data acquisition module acquires data of the speed V, the pressure P, and the temperature T once every Δ T time, calculates a primitive value within the Δ T time, and transmits the primitive value to the upper computer through the data transmission module.
Further, in step S5, by using the trained BP neural network model, calculating attribute values acquired by the data acquisition modules on the P energy nodes in each sub-grid to obtain primitive values as an input data set, and outputting the primitive values representing the whole grid of the indoor environment three-dimensional model by the trained BP neural network model, where the primitive values represent the detection values of the indoor environment of the building.
Further, in step S1, scanning the environment at least once using a 3D laser scanner to obtain a three-dimensional indoor environment model in the form of a three-dimensional point cloud; the mesh for constructing the three-dimensional indoor environment model is composed of a finite number of individual volumes, the sum of which represents the entirety of the indoor environment.
The invention also provides a building indoor environment detection system, which is used for realizing the building indoor environment detection method and comprises the following steps: the device comprises a three-dimensional model building unit, a variable processing unit, a discretization unit, a model reconstruction unit and a detection unit;
the three-dimensional model building unit is used for building a three-dimensional indoor environment model and dividing the built three-dimensional indoor environment model into grids;
the variable processing unit is used for modeling the air flow of the three-dimensional indoor environment model to form an air flow model, and the variables of the air flow model comprise speed V, pressure P and temperature T;
the discretization unit is used for calculating an element value contributing to the variation of the air flow model in each unit grid of the grid by discretizing the variables of the air flow model on the grid, selecting an element value data point, and sub-grid dividing the grid according to the element value data point;
the model reconstruction unit is used for constructing multiple models of the sub-grids, selecting P positions as energy nodes, and obtaining attribute values of the P energy nodes to perform model reconstruction on each sub-grid;
the detection unit is used for calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of a plurality of sub-grids reconstructed by the attribute values of p energy nodes in each sub-grid.
Further, the model reconstruction unit includes: the device comprises a mapping module, a multi-mode generating module, a data acquisition module and an attribute module;
the mapping module is used for searching a group of primitive value data subsets corresponding to the m-dimensional unit grids
Figure 18500DEST_PATH_IMAGE021
Making primitive value data sets on the air flow field H of the sub-grid
Figure 234718DEST_PATH_IMAGE022
To the primitive value data subsets
Figure 382802DEST_PATH_IMAGE021
Is maximum;
the multi-mode generation module is used for solving the maximum mapping primitive value data subset
Figure 141811DEST_PATH_IMAGE021
In (1)
Figure 349939DEST_PATH_IMAGE016
The m-dimensional element value data form m modes of the S subspace;
the data acquisition module is arranged at the unit grid position corresponding to the P positions with the maximum absolute value of the element value of each mode, acquires speed V, pressure P and temperature T data once every delta T time and calculates the element value in the delta T time;
the attribute module is used for selecting the p positions as energy nodes, and taking temperature, speed and pressure as attribute values of the energy nodes.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention combines the three-dimensional indoor environment model to carry out airflow modeling on the three-dimensional indoor environment model divided into the grids to form the airflow model, proposes the calculation of the whole grid of the indoor environment three-dimensional model by using the air flow field H of a plurality of sub-grids reconstructed by the attribute values of p energy nodes in each sub-grid, and can greatly improve the precision of the detection model by combining data and a physical modeling method.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a schematic flow chart of a method for detecting indoor environment of a building according to the present invention;
fig. 2 is a schematic structural diagram of a building indoor environment detection system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. 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 application.
In the drawings of the embodiments of the present invention, in order to better and more clearly describe the working principle of each element in the system, the connection relationship of each part in the apparatus is shown, only the relative position relationship between each element is clearly distinguished, and the restriction on the signal transmission direction, the connection sequence, and the size, the dimension, and the shape of each part structure in the element or structure cannot be formed.
Fig. 1 is a schematic flow chart of the method for detecting the indoor environment of the building according to the present invention. The method for detecting the indoor environment of the building comprises the following steps:
s1, establishing a three-dimensional indoor environment model, and dividing the established three-dimensional indoor environment model into grids.
The environment is scanned at least once using a 3D laser scanner to obtain a three-dimensional model of the indoor environment in the form of a three-dimensional point cloud.
The mesh for constructing the three-dimensional indoor environment model is composed of a finite number of individual volumes, the sum of which represents the entirety of the indoor environment.
And S2, forming an environment calculation area by the three-dimensional indoor environment model divided into the grids, and modeling the air flow in the environment calculation area to form an air flow model, wherein the air flow model variables comprise speed V, pressure P and temperature T.
S3, calculating a primitive value contributing to the air flow model variable in each unit grid of the grid by discretizing the air flow model variable on the grid, selecting a primitive value data point according to a possible variation range of the primitive value, and performing sub-grid division on the grid according to the primitive value data point. The generated plurality of submeshes have different sizes and are not stacked on top of each other.
And S4, constructing multiple models of the sub-grids, and performing model reconstruction on each sub-grid through the multiple models.
S41, in the air flow field H with the sub-grid of the n-dimensional unit grid, n element values corresponding to each unit grid form a group of element value data sets, the element values corresponding to the m-dimensional unit grid form element value data subsets, and the element value data subsets form S subspaces (m is the m of the element value data subsets)<n), i.e. finding an optimal set of primitive value data subsets
Figure 53452DEST_PATH_IMAGE001
Such that primitive value data sets on the air flow field H of the submesh
Figure 880594DEST_PATH_IMAGE002
To the primitive value data subsets
Figure 618743DEST_PATH_IMAGE001
Can be expressed by the following formula (1):
Figure 997772DEST_PATH_IMAGE023
（1）；
in the formula (I), the compound is shown in the specification,
Figure 329527DEST_PATH_IMAGE004
，
Figure 819414DEST_PATH_IMAGE005
is the energy norm of the air flow field H,
Figure 412069DEST_PATH_IMAGE006
is the desired operator.
S42, primitive values on air flow field H of sub-grid at any time t
Figure 837366DEST_PATH_IMAGE007
Can be averaged by its velocity field
Figure 515472DEST_PATH_IMAGE008
Pressure field
Figure 74629DEST_PATH_IMAGE009
And temperature field
Figure 397157DEST_PATH_IMAGE010
Is expressed by the sum of (1) as shown in formula (2):
Figure 852409DEST_PATH_IMAGE011
(2)；
converting the optimal problem found in the formula (1) into a characteristic value problem, as shown in the formula (3):
Figure 283391DEST_PATH_IMAGE012
(3)；
in the formula (I), the compound is shown in the specification,
Figure 984587DEST_PATH_IMAGE013
is the product of the standard tensor in the form of,
Figure 551835DEST_PATH_IMAGE014
is composed of
Figure 443567DEST_PATH_IMAGE015
The dual primitive values of (1). Wherein, the solution obtained in the formula (3)
Figure 971632DEST_PATH_IMAGE016
The number of (c) is the primitive value data of the multi-model of the desired construction submesh,
Figure 607013DEST_PATH_IMAGE017
for corresponding eigenvalues, at which point the solution is obtained
Figure 763187DEST_PATH_IMAGE016
If the number of (2) is m, the m-dimensional element value data constitutes m patterns of the S subspace.
S43, for the obtained m modes, arranging a data acquisition module at a unit grid position corresponding to the P position with the maximum primitive value absolute value of each mode; the data acquisition module acquires speed V, pressure P and temperature T data once every delta T time, calculates element values in the delta T time and transmits the element values to the upper computer through the data transmission module; under the condition that an indoor air flow field is stable, the m-dimensional element value data can be integrally reflected through the sum of fluid speed values, pressure values and temperature values acquired from p positions.
S44, selecting the P positions as energy nodes, taking the temperature, the speed and the pressure as attribute values of the energy nodes, and realizing the real-time reconstruction of the air flow field H of the sub-grid through the attribute values of the P energy nodes acquired on the plane of the air flow field H of the sub-grid to be reconstructed in real time.
p energy nodes, the modulus coefficient b of the air flow field H of the sub-grid at any moment k Is estimated value of
Figure 966767DEST_PATH_IMAGE018
The estimation can be performed by the components of the attribute of the energy node acquired by the P energy nodes in real time:
Figure 841182DEST_PATH_IMAGE019
(4)；
wherein the content of the first and second substances,
Figure 545833DEST_PATH_IMAGE020
for the ith energy node at the time t, the coordinate is x i The component of the property value at (c).
Based on the model, the real-time reconstruction of the air flow field H of the sub-grid can be realized through the attribute values of P energy nodes acquired in real time on the plane of the air flow field H of the sub-grid to be reconstructed.
And S5, calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of the multiple sub-grids reconstructed by the attribute values of the p energy nodes in each sub-grid.
Using a BP neural network model may be based on a plurality of reconstructed sub-meshesAir flow field H for continuously calculating integral grid of indoor environment three-dimensional model 0 。
The learning process of the BP neural network algorithm is divided into two stages, namely forward propagation of signals and backward propagation of errors. In the forward propagation stage, sample data is input into an input layer, and a final output value is obtained after calculation and processing layer by layer of each hidden layer; in the back propagation stage, if the error between the actual output value and the expected value does not reach the preset precision, the difference between the output value and the expected value is calculated layer by layer recursively, and the weight of each layer is adjusted by a gradient descent method to minimize the final error.
Because the change of the air flow field is a continuous process, namely the attribute value of the air flow field at the previous moment influences the attribute value at the next moment, the element value obtained by calculating the attribute values of p positions collected in real time in each sub-grid is selected as the input variable of the training sample, and the final output variable is the element value of the whole grid of the indoor environment three-dimensional model formed in the plurality of sub-grids. Over time, the sensor nodes upload new data and update the new data into the training samples.
And calculating attribute values, namely a speed value, a pressure value and a temperature value, which are acquired by the data acquisition modules on the P energy nodes in each sub-grid by using the trained BP neural network model and using the attribute values as an input data set, wherein the trained BP neural network model can output a primitive value representing the whole grid of the indoor environment three-dimensional model, and the primitive value represents the indoor environment detection value of the building.
As shown in fig. 2, which is a schematic structural diagram of a building indoor environment detection system of the present invention, the building indoor environment detection system includes: the device comprises a three-dimensional model building unit, a variable processing unit, a discretization unit, a model reconstruction unit and a detection unit.
And the three-dimensional model building unit is used for building a three-dimensional indoor environment model and dividing the built three-dimensional indoor environment model into grids.
And the variable processing unit is used for modeling the air flow of the three-dimensional indoor environment model to form an air flow model, and the air flow model variables comprise speed V, pressure P and temperature T.
And the discretization unit is used for calculating an element value contributing to the air flow model variable in each unit grid of the grid by discretizing the air flow model variable on the grid, selecting an element value data point according to a possible variation range of the element value, and sub-grid division is carried out on the grid according to the element value data point.
The model reconstruction unit is used for constructing multiple models of the sub-grids and performing model reconstruction on each sub-grid through the multiple models.
The model reconstruction unit includes: the device comprises a mapping module, a multi-mode generating module, a data acquisition module and an attribute module.
The mapping module is used for searching a group of primitive value data subsets corresponding to the m-dimensional unit grids
Figure 963039DEST_PATH_IMAGE024
Making primitive value data sets on the air flow field H of the sub-grid
Figure 196574DEST_PATH_IMAGE022
To the primitive value data subset
Figure 558285DEST_PATH_IMAGE025
The mapping of (2) is maximal.
The multi-mode generation module is used for solving the maximum mapping primitive value data subset
Figure 676414DEST_PATH_IMAGE026
In (1)
Figure 807181DEST_PATH_IMAGE016
M, the m-dimensional primitive value data form m patterns of the S subspace.
The data acquisition module is arranged at the unit grid position corresponding to the P positions with the maximum element value absolute value of each mode, acquires speed V, pressure P and temperature T data once every delta T time and calculates the element value in the delta T time.
The attribute module is used for selecting the p positions as energy nodes, and taking temperature, speed and pressure as attribute values of the energy nodes.
The detection unit is used for calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of a plurality of sub-grids reconstructed by p energy nodes.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in or transmitted over a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (7)

1. A building indoor environment detection method is characterized by comprising the following steps:
s1, establishing a three-dimensional indoor environment model, and dividing the established three-dimensional indoor environment model into grids;
s2, performing airflow modeling on the three-dimensional indoor environment model divided into the grids to form an airflow model;
s3, discretizing variables of the airflow model on grids, calculating element values contributing to the variables of the airflow model in each unit grid, selecting element value data points, and sub-grid dividing the grids according to the element value data points;
s4, constructing multiple models of the sub-grids, selecting P positions as energy nodes, and obtaining attribute values of the P energy nodes to perform model reconstruction on each sub-grid;
s41, in an air flow field H with a sub-grid of n-dimensional unit grids, n primitive values respectively corresponding to each unit grid form a group of primitive value data sets, the primitive values corresponding to m-dimensional unit grids form primitive value data subsets, and an optimal primitive value data subset is searched
Figure QLYQS_1
Such that the primitive value data set on the air flow field H of the subgrid, { θ } i To the primitive value data subsets
Figure QLYQS_2
Maximum projection of (d):
Figure QLYQS_3
wherein, { θ } i ∈H|i＝1，2…n}，
Figure QLYQS_4
Is the energy norm of the air flow field H,
Figure QLYQS_5
is a desired operator;
s42, primitive value theta on air flow field H of sub-grid at any time t i (t) average velocity field θ from a plurality of unit meshes iV (t) pressureField theta iP (t) and temperature field θ iT (t) is represented by the sum of formula (2):
θ i (t)＝θ iV (t)+θ iP (t)+θ iT (t) (2)；
converting formula (1) into a characteristic value problem, as shown in formula (3):
Figure QLYQS_6
in the formula (I), the compound is shown in the specification,
Figure QLYQS_7
is the product of the standard tensor, θ * ∈H * Solved for dual primitive values of theta
Figure QLYQS_8
The number of which constitutes a plurality of patterns of the sub-grid, τ i Is the corresponding characteristic value;
s43, for the m obtained modes, arranging a data acquisition module at a unit grid position corresponding to P positions with the maximum element value absolute value of each mode, and calculating the m-dimensional element value data according to a formula (2) by using speed values, pressure values and temperature values acquired from the P positions;
s44, selecting the p positions as energy nodes, taking the temperature, the speed and the pressure as attribute values of the energy nodes, and realizing real-time reconstruction of an air flow field of the sub-grid through the attribute values of the p energy nodes;
and S5, calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of the multiple sub-grids reconstructed by the attribute values of the p energy nodes in each sub-grid.
2. The method according to claim 1, wherein in step S44, the p energy nodes are the modulus coefficients b of the air flow field of the sub-grid at any time k Is estimated value of
Figure QLYQS_9
Estimating the components of the attribute of the energy nodes acquired by the P energy nodes in real time:
Figure QLYQS_10
wherein, theta (x) i T) is the ith energy node at the time t and has the coordinate x i The component of the property value at (c).
3. The method for detecting the indoor environment of the building according to claim 1, wherein in step S43, the data acquisition module acquires data of the speed V, the pressure P and the temperature T once every Δ T time, calculates a primitive value within the Δ T time, and transmits the primitive value to the upper computer through the data transmission module.
4. The method for detecting the indoor environment of the building as claimed in claim 1, wherein in step S5, a trained BP neural network model is used to calculate the attribute values collected by the data collection modules on the P energy nodes in each sub-grid to obtain primitive values as an input data set, and then the trained BP neural network model outputs primitive values representing the whole grid of the three-dimensional model of the indoor environment, and the primitive values represent the detection values of the indoor environment of the building.
5. The method for detecting the indoor environment of the building according to claim 1, wherein in step S1, the environment is scanned at least once using a 3D laser scanner to obtain a three-dimensional indoor environment model in the form of a three-dimensional point cloud; the mesh that builds the three-dimensional indoor environment model is made up of a finite number of individual volumes, the sum of which represents the entirety of the indoor environment.
6. A building indoor environment detection system for implementing the building indoor environment detection method of any one of claims 1 to 5, comprising: the device comprises a three-dimensional model building unit, a variable processing unit, a discretization unit, a model reconstruction unit and a detection unit;
the three-dimensional model building unit is used for building a three-dimensional indoor environment model and dividing the built three-dimensional indoor environment model into grids;
the variable processing unit is used for modeling the air flow of the three-dimensional indoor environment model to form an air flow model, and the variables of the air flow model comprise speed V, pressure P and temperature T;
the discretization unit is used for calculating an element value contributing to the variation of the air flow model in each unit grid of the grid by discretizing the variables of the air flow model on the grid, selecting an element value data point, and sub-grid dividing the grid according to the element value data point;
the model reconstruction unit is used for constructing multiple models of the sub-grids, selecting P positions as energy nodes, and obtaining attribute values of the P energy nodes to perform model reconstruction on each sub-grid;
the detection unit is used for calculating the whole grid of the indoor environment three-dimensional model by using the air flow field H of the multiple sub-grids reconstructed by the attribute values of the p energy nodes in each sub-grid.
7. The building indoor environment detection system according to claim 6, wherein the model reconstruction unit includes: the device comprises a mapping module, a multi-mode generating module, a data acquisition module and an attribute module;
the mapping module is used for searching a group of primitive value data subsets corresponding to the m-dimensional unit grids
Figure QLYQS_11
Such that the primitive value data set on the air flow field H of the subgrid θ i To the primitive value data subsets
Figure QLYQS_12
Is maximum;
the multi-mode generation module is used for solving the maximum mapping primitive value data subset
Figure QLYQS_13
In (1)
Figure QLYQS_14
M, the m-dimensional elementary value data form m modes of the S subspace;
the data acquisition module is arranged at the position of the unit grid corresponding to the P positions with the maximum absolute value of the element value of each mode, acquires speed V, pressure P and temperature T data once every delta T time and calculates the element value in the delta T time;
the attribute module is used for selecting the p positions as energy nodes, and taking the temperature, the speed and the pressure as attribute values of the energy nodes.
CN202211576539.2A 2022-12-09 2022-12-09 Building indoor environment detection system and detection method Active CN115577606B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211576539.2A CN115577606B (en) 2022-12-09 2022-12-09 Building indoor environment detection system and detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211576539.2A CN115577606B (en) 2022-12-09 2022-12-09 Building indoor environment detection system and detection method

Publications (2)

Publication Number Publication Date
CN115577606A CN115577606A (en) 2023-01-06
CN115577606B true CN115577606B (en) 2023-03-14

Family

ID=84590087

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211576539.2A Active CN115577606B (en) 2022-12-09 2022-12-09 Building indoor environment detection system and detection method

Country Status (1)

Country Link
CN (1) CN115577606B (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110189412B (en) * 2019-05-13 2023-01-03 武汉大学 Multi-floor indoor structured three-dimensional modeling method and system based on laser point cloud
CN110737935B (en) * 2019-09-18 2022-07-22 同济大学 Indoor thermal environment modeling method based on digital twinning
CN114663629A (en) * 2022-04-15 2022-06-24 安徽安联云服务有限公司 Building scene modeling method

Also Published As

Publication number Publication date
CN115577606A (en) 2023-01-06

Similar Documents

Publication Publication Date Title
Adeli et al. Dynamic fuzzy wavelet neural network model for structural system identification
WO2017031718A1 (en) Modeling method of deformation motions of elastic object
CN110377942B (en) Multi-model space-time modeling method based on finite Gaussian mixture model
Saranyasoontorn et al. A comparison of standard coherence models for inflow turbulence with estimates from field measurements
Eweis-Labolle et al. Data fusion with latent map Gaussian processes
CN106842112A (en) Sound localization method based on parametrization Bayes&#39;s dictionary learning under strong reverberant ambiance
CN114216582B (en) High-precision rapid temperature field reconstruction method, system, equipment and terminal
CN116451584A (en) Thermal stress prediction method and system based on neural network
CN113255181A (en) Heat transfer inverse problem identification method and device based on deep learning
CN114912364A (en) Natural gas well flow prediction method, device, equipment and computer readable medium
CN115577606B (en) Building indoor environment detection system and detection method
Hart et al. Machine-learning of long-range sound propagation through simulated atmospheric turbulence
CN115062551B (en) Wet physical process parameterization method based on time sequence neural network
CN111159956A (en) Feature-based flow field discontinuity capturing method
CN113065321B (en) User behavior prediction method and system based on LSTM model and hypergraph
CN115114985A (en) Sensor system distributed fusion method based on set theory
CN114881506A (en) Heat supply demand load assessment method and system based on room temperature and IBA-LSTM
CN114221334A (en) Rapid state estimation method based on graph neural network
CN111914402B (en) Dynamic topology estimation system and method based on signal characteristics and topology change priori
Gong et al. A visualization system for calibrating multimodel ensembles in weather forecast
Pedder et al. The semi‐geostrophic diagnosis of vertical motion. I: Formulation and coordinate transformations
CN117057212B (en) Acoustic reconstruction method for dynamic temperature field of nuclear power device
CN115951405B (en) Speed change imaging method based on sparse convolution and adaptive moment estimation
CN114004175B (en) Method for quickly searching global wall surface distance and dimensionless wall surface distance
Lawal et al. Assessing the Feasibility of Wave Energy Harvesting through Coastal Wave Modeling and Forecasting with Long Short-Term Memory Optimization using Univariate Time Series Approach

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