CN115063040A - Method and system for collaborative evaluation and prediction of house building structure health - Google Patents
Method and system for collaborative evaluation and prediction of house building structure health Download PDFInfo
- Publication number
- CN115063040A CN115063040A CN202210895806.6A CN202210895806A CN115063040A CN 115063040 A CN115063040 A CN 115063040A CN 202210895806 A CN202210895806 A CN 202210895806A CN 115063040 A CN115063040 A CN 115063040A
- Authority
- CN
- China
- Prior art keywords
- data
- health
- structural
- building
- state
- 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.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims abstract description 62
- 238000000547 structure data Methods 0.000 claims abstract description 19
- 238000010586 diagram Methods 0.000 claims abstract description 18
- 230000008447 perception Effects 0.000 claims abstract 2
- 230000008569 process Effects 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000009435 building construction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Primary Health Care (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for collaborative evaluation and prediction of house building structure health, wherein the method comprises the steps of collecting data of structural members; the data includes geometry data, state data, and condition data; building a house building feature map according to the geometric structure data to obtain a structure feature vector; obtaining a state data matrix according to the state data and the state data; obtaining a current health evaluation value and a predicted health evaluation value according to the structural feature vector and the state data matrix; the current health evaluation value is used for evaluating the current health state of the house building; the predicted health assessment value is used for predicting the future health state of the building. The system comprises a data intelligent perception module and an evaluation and prediction module. The house building characteristic diagram constructed by the method can reflect the relationship between the geometric structure data of each structural member and the house building structure health, and the state data matrix is combined to evaluate and predict the structure health state of the house building.
Description
Technical Field
The invention relates to the technical field of health assessment and prediction of building structures, in particular to a method and a system for collaborative assessment and prediction of the health of the building structures.
Background
In recent years, self-building collapse accidents occur in many countries, which cause serious casualties and property loss. After the accident happens, the residential building department deploys the special safety treatment of the national self-building houses. Especially, the self-building house in rural areas of China has huge base numbers, the construction peak period is about 2000 years, and after the service life of 10 to 20 years, the safety problem of the self-building house in recent years can be intensively developed. How to predict the building structure condition, send out early warning for the building when the house structure is unusual serious under special weather condition, specific use operation situation, protection national property and people's safety become the problem that needs to solve urgently.
At present, although the conventional manual nondestructive detection method can detect the health state of a building structure, the monitoring work is time-consuming and labor-consuming due to the relatively large scale of houses and the large number base of the houses; if the monitored building is involved in an operational activity, it may also be necessary to interrupt the operational activity. The existing automatic building structure health monitoring system is characterized in that various sensors are installed at different positions in a building, monitoring data acquired by the sensors are uniformly sent to a monitoring computer, and the data are evaluated to generate a health evaluation result. In the method, various sensors need to be permanently installed on a house, the cost is high, and the sensors need to be maintained at a later stage to ensure that the system can normally work; secondly, the existing building structure health detection or prediction method only considers the factors (such as foundation settlement, temperature change and the like) causing additional deformation or constraint deformation of the building structure, namely, the detection or prediction basis is based on the state data of each structural member (beam, plate, column, wall, foundation and the like), and the spatial layout of each structural member in the detected building is ignored. Because even if the observed data (such as foundation settlement data, wall inclination data, crack data and the like) of the two building buildings are the same through the sensor, the health conditions of the two building buildings are not necessarily the same due to different building structures. Especially, a large number of self-built houses have the phenomenon of private reconstruction of engineering bearing structures, so that the influence of the spatial layout of structural components in the house building on the health of the house building structure cannot be ignored during the prediction of the health of the house building structure.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the shortcomings of the prior art for detecting the health of the building structure, so as to provide a method for the collaborative assessment and prediction of the health of the building structure.
The invention provides a method for collaborative evaluation and prediction of building structure health, which comprises the following steps:
s1: collecting data of the structural member; the data includes geometry data, state data, and condition data;
s2: building a house building feature map according to the geometric structure data to obtain a structure feature vector; obtaining a state data matrix according to the state data and the state data;
s3: obtaining a current health evaluation value and a predicted health evaluation value according to the structural feature vector and the state data matrix; the current health evaluation value is used for evaluating the current health state of the house building; the predicted health assessment value is used for predicting the future health state of the building.
Preferably, in S1, the process of acquiring the geometric data is: surveying and mapping a structural drawing of a house building; determining geometric structure data of the structural member according to a structural drawing of the house building;
the process of collecting the state data is as follows: setting an observation point on a house building, installing a sensor at the observation point, and periodically and repeatedly observing the observation point through the sensor to obtain state data, wherein the state data comprises newly observed state data and past observed state data;
the process of collecting the condition data is as follows: the daily use condition and the operation condition of the house building are determined in a manual recording mode, and the condition data are obtained according to the daily use condition and the operation condition.
Preferably, the geometry data comprises position data of the structural member; the state data comprises foundation settlement data, concrete strength data, member strength data, crack data, strain data, wall inclination data, horizontal displacement data, vibration data and building structure load data; the condition data includes personnel activity, major load sources, building age, maximum passenger flow, and specific business activities.
Preferably, in S2, the process of constructing the house building feature map according to the geometric data is as follows:
step 1: surveying and mapping a structural drawing of a house building; determining the spatial layout of structural members according to a structural drawing of a house building; the spatial layout is geometric structure data;
step 2: the method comprises the following steps of surveying and mapping structural drawings of structural members, and determining the connection mode among the structural members and the attributes of the structural members according to the structural drawings of the structural members;
and step 3: according to the geometric structure data, the connection mode among the structural components and the attributes of the structural components, the house building is drawn into a house building characteristic diagram; the house building characteristic graph comprises nodes and edges; the node is a structural member; the sides are the connection between the structural members.
Preferably, in S2, the process of obtaining the structural feature vector is as follows: inputting the house building feature map into a convolutional neural network, and obtaining a structural feature vector by the convolutional neural network according to nodes and edges; the structural feature vector, noted:
(ii) a The structural feature vector comprises a plurality of elements; a plurality of elements are obtained according to an activation function in the convolutional neural network, and the value of each element is between 0 and 1; the convolutional neural network is a graph convolutional neural network.
Preferably, in S2, the state data matrix includes a current state data matrix and a past state data matrix;
constructing a current state data matrix by taking the structural member as a matrix element and the latest observed state data and status data as element attributes;
and constructing a past state data matrix by taking the structural member as a matrix element and taking the past observed state data and the state data as element attributes.
Preferably, in S3, the process of obtaining the current health assessment value is: constructing a data set according to the data, and training a linear layer model according to the data set; inputting the structural feature vector and the current state data matrix into the trained linear layer model for calculation to obtain a current health evaluation value, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
representing a current health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
data matrix representing current state
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector.
Preferably, in S3, the process of obtaining the predicted health assessment value is: training a prediction model according to the data set, and inputting a past state data matrix into the trained prediction model to obtain a predicted state data matrix; inputting the predicted state data matrix and the structural feature vector into the trained linear layer model for calculation to obtain a predicted health evaluation value, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
representing a predicted health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
state data matrix representing predictions
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector.
Preferably, the structural drawing of the house building comprises a general building plan, a building elevation and a building section; the structural drawing of the structural member comprises a member section size, a member reinforcement diagram, a structural plane arrangement diagram and a node connection structure detail diagram.
The invention also provides a system for the collaborative evaluation and prediction of the health of the house building structure, which is applied to the method and comprises the following steps: the system comprises a data intelligent sensing module and an evaluation and prediction module; the data intelligent sensing module comprises a sensor and is used for acquiring data of the structural member; the evaluation and prediction module comprises a component-component interaction module and a component state-house structure health state correlation module; the component-component interaction module is used for obtaining a structural feature vector according to the geometric structure data; the component state-house structure health state correlation module comprises a linear layer model and a prediction model; the component state-house structure health state correlation module is used for evaluating the house building structure health through the linear layer model to obtain a current health evaluation value, and predicting the house building structure health through the prediction model and the linear layer model to obtain a predicted health evaluation value.
The technical scheme of the invention has the following advantages: the method overcomes the defect that the state data of the building structure is generally used only to evaluate or predict the health state of the building structure in the prior art; the building characteristic diagram constructed by the method can reflect the relationship between the geometric structure data of each structural component and the structural health of the building, and the structural health state of the building is evaluated and predicted by combining the state data matrix.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for collaborative assessment and prediction of building structure health in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of data acquisition in the practice of the present invention;
FIG. 3 is a flow chart of building construction profile construction in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart of obtaining a current health assessment value in the practice of the present invention;
FIG. 5 is a flow chart of obtaining a predicted health assessment value in an implementation of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, the present embodiment provides a method for collaborative assessment and prediction of building structure health, the method comprising:
s1: collecting data of a structural member; the data includes geometry data, state data, and condition data;
in this embodiment, the structural members include, but are not limited to, foundations, load-bearing walls, columns, stairways, windows, doors, and rebar.
Specifically, as shown in fig. 2, in the present embodiment, data collection is performed on houses of six common building structures from three dimensions, namely, collecting geometry data from a geometry structure, collecting status data from a structural state, and collecting status data from a use/operation activity;
the process of acquiring the geometric data is as follows: surveying and mapping a structural drawing of a house building; determining geometric structure data of the structural member according to a structural drawing of the house building;
the process of collecting the state data is as follows: setting observation points on a house building, installing different sensors at different observation points, and periodically and repeatedly observing the observation points through various sensors to obtain state data, wherein the state data comprises newly observed state data and past observed state data; the practical situation is exemplified as follows: observing once a week, and acquiring observation data every week; using the newly observed state data if the current health state of the building needs to be evaluated; if a predicted state data matrix needs to be obtained, using the state data of past observation; in this embodiment, the sensor includes, but is not limited to, a static level, an inclination sensor, a stress detector, a crack meter, and a strain gauge;
the process of collecting the condition data is as follows: the daily use condition and the operation condition of the house building are determined in a manual recording mode, and the condition data are obtained according to the daily use condition and the operation condition.
In the present embodiment, as shown in fig. 2, the geometry data includes position data of the structural member; the state data comprises foundation settlement data, concrete strength data, member strength data, crack data, strain data, wall inclination data, horizontal displacement data, vibration data and building structure load data; the condition data includes personnel activity, major load sources, building age, maximum passenger flow, and specific business activities.
S2: building a house building feature map according to the geometric structure data to obtain a structure feature vector; obtaining a state data matrix according to the state data and the state data;
specifically, as shown in fig. 3, the house building is graphically represented according to the geometric data, and the process of constructing the house building feature map according to the geometric data is as follows:
step 1: surveying and mapping a structural drawing of a house building; determining the spatial layout of structural members according to a structural drawing of a house building; the spatial layout is geometric structure data;
step 2: the method comprises the following steps of surveying and mapping structural drawings of structural members, and determining the connection mode among the structural members and the attributes of the structural members according to the structural drawings of the structural members;
and step 3: according to the geometric structure data, the connection mode among the structural components and the attributes of the structural components, the house building is drawn into a house building characteristic diagram; the house building characteristic graph comprises nodes and edges; the node is a structural member; the sides are the connection between the structural members.
In the present embodiment, the structural drawing of the house building includes a general plan view of the building, an elevation view of the building, and a section view of the building; the structural drawing of the structural member comprises a member section size, a member reinforcement diagram, a structural plane arrangement diagram and a node connection structure detail diagram.
The process of obtaining the structural feature vector is as follows: inputting the house building feature map into a convolutional neural network, and obtaining a structural feature vector by the convolutional neural network according to nodes and edges; the structural feature vector, noted:
(ii) a The structural feature vector comprises a plurality of elements; the multiple elements are all obtained according to the activation function in the convolutional neural network, and the values of the elements are between 0 and 1, namely
(ii) a The convolutional neural network in this embodiment is a Graph Convolutional Neural Network (GCNN).
The activation function expression is:
the traditional house building safety monitoring can only achieve 'independent measurement', so that unified house building structural state data and house building structural health data corresponding to the current state are lacked, a large number of data sets are needed in a general deep learning algorithm, the relation between the spatial layout of structural components and the house building structural health can be learned through a graph convolution neural network, and therefore dependence on the structural state data and the house building structural health data corresponding to the current state can be remarkably reduced.
Expressing the state of the house building from two dimensions of state data and state data to construct a state data matrix;
specifically, the state data matrix comprises a current state data matrix and a past state data matrix;
constructing a current state data matrix by taking the structural member as a matrix element and the latest observed state data and status data as element attributes;
and constructing a past state data matrix by taking the structural member as a matrix element and taking the past observed state data and the state data as element attributes.
Table 1 is a state data matrix form;
as can be seen from table 1, the form of the state data matrix (7 × n matrix); as shown in Table 1, the rows of the table represent structural members, and the columns represent state data and status data (element attributes) of the structural members; the attribute 1-attribute n can be set to data included in the status data and the status data; the more the attribute is set, the more meticulous the state and the condition of the house building are depicted, which is more beneficial to the later evaluation and prediction, so that the health evaluation and prediction are more accurate. Data such as foundation settlement and cracks, which are continuous attributes (e.g., foundation settlement data of 6.7cm, which may indicate 6.7cm settlement for the foundation construction); the data of business category and the like is a nominal attribute, i.e., a nominal value represents a category of a house building engaged in a certain business (e.g., 1-self-housing, 2-hotel, 3-restaurant, 4-cinema, etc.).
S3: obtaining a current health evaluation value and a predicted health evaluation value according to the structural feature vector and the state data matrix; the current health evaluation value is used for evaluating the current health state of the house building; the predicted health assessment value is used for predicting the future health state of the building.
Specifically, as shown in fig. 4, a characteristic diagram of a house building is a house building characteristic diagram, a component-component interaction (SSI) is a graph convolution neural network, a structural characteristic vector of the house building is a structural characteristic vector, structural state data is a current state data matrix, a linear layer is a trained linear layer model, and an evaluation value of the current house building health is a current health evaluation value; the process of obtaining the current health assessment value is as follows: constructing a data set according to the data, and training a linear layer model according to the data set; inputting the structural feature vector and the current state data matrix into the trained linear layer model for calculation to obtain a current health evaluation value; the formula for calculating the linear layer as in fig. 4 is:
wherein the content of the first and second substances,
representing a current health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
data matrix representing current state
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector; since the sigmoid activation function takes values between (0, 1), multiplication by 100 makes the current health assessment value a value of 0-100, which is used to represent the degree of health.
As shown in fig. 5, the characteristic diagram of the house building is a house building characteristic diagram, the component-component interaction (SSI) is a graph convolution neural network, the structural characteristic vector of the house building is a structural characteristic vector, the historical structural state data is a past state data matrix, the LSTM prediction model is a prediction model, the linear layer is a trained linear layer model, and the predicted future house building health value is a predicted health evaluation value; the process of obtaining the predicted health assessment value is as follows: training a prediction model according to the data set, and inputting a past state data matrix into the trained prediction model to obtain a predicted state data matrix; inputting the predicted state data matrix and the structural feature vector into the trained linear layer model for calculation to obtain a predicted health evaluation value; the formula for the calculation of the linear layer as in fig. 5 is:
wherein the content of the first and second substances,
represents a predicted health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
state data matrix representing predictions
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector; since the sigmoid activation function takes values between (0, 1), multiplication by 100 results in a value of the predicted health assessment value of 0-100, which is used to represent the degree of health. The prediction model is constructed based on the long-short term memory network (LSTM) in this embodiment.
In this embodiment, there is also provided a system for collaborative assessment and prediction of building structure health, which is applied to the method described above and includes: the system comprises a data intelligent sensing module and an evaluation and prediction module; the data intelligent sensing module comprises a sensor and is used for acquiring data of the structural member; the evaluation and prediction Module comprises a component-component Interaction Module (SSIM), a component state-building Structure Health state association Module (SHIM); the component-component interaction module is used for obtaining a structural feature vector according to the geometric structure data; the component state-house structure health state correlation module comprises a linear layer model and a prediction model; the component state-house structure health state correlation module is used for evaluating the house building structure health through the linear layer model to obtain a current health evaluation value, and predicting the house building structure health through the prediction model and the linear layer model to obtain a predicted health evaluation value.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A method for collaborative assessment and prediction of building structure health, comprising:
s1: collecting data of the structural member; the data includes geometry data, state data, and condition data;
s2: building a house building feature map according to the geometric structure data to obtain a structure feature vector; obtaining a state data matrix according to the state data and the state data;
s3: obtaining a current health evaluation value and a predicted health evaluation value according to the structural feature vector and the state data matrix; the current health assessment value is used for assessing the current health state of the house building; the predicted health assessment value is used for predicting the future health state of the building.
2. The method for collaborative assessment and prediction of building construction health according to claim 1, wherein in S1, the process of collecting said geometric data is: surveying and mapping a structural drawing of a house building; determining the geometric structure data of the structural member according to a structural drawing of the house building;
the process of collecting the state data is as follows: setting an observation point on a house building, installing a sensor at the observation point, and periodically and repeatedly observing the observation point through the sensor to obtain the state data, wherein the state data comprises the latest observed state data and the past observed state data;
the process of collecting the condition data is as follows: and determining the daily use condition and the operational activity condition of the house building in a manual recording mode, and obtaining the condition data according to the daily use condition and the operational activity condition.
3. A method for collaborative assessment and prediction of building construction structural health according to claim 2, characterized in that said geometric data includes position data of structural members; the state data comprises foundation settlement data, concrete strength data, member strength data, crack data, strain data, wall inclination data, horizontal displacement data, vibration data and building structure load data; the condition data includes personnel activity, major load sources, building age, maximum passenger flow, and specific business activities.
4. The method for collaborative assessment and prediction of building construction health according to claim 3, wherein in S2, the process of constructing the building construction feature map according to the geometric structure data comprises:
step 1: surveying and mapping a structural drawing of a house building; determining the spatial layout of structural members according to a structural drawing of a house building; the spatial layout is the geometric structure data;
step 2: the method comprises the following steps of surveying and mapping structural drawings of structural members, and determining the connection mode among the structural members and the attributes of the structural members according to the structural drawings of the structural members;
and step 3: according to the geometric structure data, the connection mode among the structural components and the attributes of the structural components, the house building is drawn into a house building characteristic diagram; the house building characteristic graph comprises nodes and edges; the node is a structural member; the sides are the connection between the structural members.
5. The method for collaborative assessment and prediction of building construction structural health according to claim 4, wherein in S2, the process of obtaining said structural feature vector is: inputting the house building feature map into a convolutional neural network, and obtaining the structural feature vector by the convolutional neural network according to the nodes and the edges; the structural feature vector is recorded as:
(ii) a The structural feature vector comprises a plurality of elements; a plurality of elements are obtained according to an activation function in the convolutional neural network, and the value of each element is between 0 and 1; the convolutional neural network is a graph convolutional neural network.
6. The method for collaborative assessment and prediction of building construction health according to claim 5, wherein in S2, said state data matrix comprises a current state data matrix and a past state data matrix;
constructing a current state data matrix by taking the structural member as a matrix element and taking the latest observed state data and state data as element attributes;
and constructing a past state data matrix by taking the structural member as a matrix element and taking the state data and the state data of past observation as element attributes.
7. The method for collaborative assessment and prediction of building construction health according to claim 6, wherein in S3, the process of obtaining said current health assessment value is: constructing a data set according to the data, and training a linear layer model according to the data set; inputting the structural feature vector and the current state data matrix into the trained linear layer model for calculation to obtain the current health assessment value, wherein the calculation formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
representing a current health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
data matrix representing current state
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector.
8. The method for collaborative assessment and prediction of building construction health according to claim 7, wherein in S3, the process of obtaining said predicted health assessment value is: training a prediction model according to the data set, and inputting a past state data matrix into the trained prediction model to obtain a predicted state data matrix; inputting the predicted state data matrix and the structural feature vector into a trained linear layer model for calculation to obtain the predicted health assessment value, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
represents a predicted health assessment value;
a transposed vector representing a weight W obtained by training the linear layer model;
state data matrix representing predictions
The transposed matrix of (2);
representing a structural feature vector;
representing a bias vector.
9. The method for collaborative assessment and prediction of building construction structural health of claim 4, wherein the structural drawing of the building construction comprises a general plan view of the building, an elevation view of the building, and a section view of the building; the structural drawing of the structural member comprises a member section size, a member reinforcement diagram, a structural plane arrangement diagram and a node connection structure detail diagram.
10. A system for collaborative assessment and prediction of building structure health, which is applied to the method for collaborative assessment and prediction of building structure health according to any one of claims 1 to 9, and comprises a data intelligent perception module, an assessment and prediction module; the data intelligent sensing module comprises a sensor and is used for acquiring data of the structural member; the evaluation and prediction module comprises a component-component interaction module and a component state-house structure health state correlation module; the component-component interaction module is used for obtaining a structural feature vector according to the geometric structure data; the component state-house structure health state correlation module comprises a linear layer model and a prediction model; the component state-house structure health state correlation module is used for evaluating the house building structure health through a linear layer model to obtain a current health evaluation value and predicting the house building structure health through a prediction model and the linear layer model to obtain a predicted health evaluation value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210895806.6A CN115063040B (en) | 2022-07-28 | 2022-07-28 | Method and system for collaborative evaluation and prediction of house building structure health |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210895806.6A CN115063040B (en) | 2022-07-28 | 2022-07-28 | Method and system for collaborative evaluation and prediction of house building structure health |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115063040A true CN115063040A (en) | 2022-09-16 |
| CN115063040B CN115063040B (en) | 2022-11-08 |
Family
ID=83205622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210895806.6A Active CN115063040B (en) | 2022-07-28 | 2022-07-28 | Method and system for collaborative evaluation and prediction of house building structure health |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063040B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629144A (en) * | 2018-06-11 | 2018-10-09 | 湖北交投智能检测股份有限公司 | A kind of bridge health appraisal procedure |
| CN109099975A (en) * | 2018-09-29 | 2018-12-28 | 上海大学 | A kind of building structure health monitoring systems |
| CN109883474A (en) * | 2019-02-20 | 2019-06-14 | 吉林建筑大学 | Building health monitoring systems and monitoring method based on field monitoring |
| CN110276542A (en) * | 2019-06-18 | 2019-09-24 | 合肥工业大学 | Complex equipment health state evaluation method based on ANP |
| WO2020200847A1 (en) * | 2019-04-03 | 2020-10-08 | Peri Gmbh | Automatic prediction of the usability of concrete for at least one intended use at a construction site |
| CN111795978A (en) * | 2020-09-08 | 2020-10-20 | 湖南大学 | Steel bridge structure health state assessment method, device, equipment and storage medium |
| CN111983459A (en) * | 2020-07-18 | 2020-11-24 | 武汉数值仿真技术研究院有限公司 | Health state testing and evaluating method based on vehicle lithium ion battery |
| CN113237885A (en) * | 2021-04-22 | 2021-08-10 | 西安石油大学 | Building performance evaluation method based on structural health monitoring data |
| CN113869774A (en) * | 2021-10-13 | 2021-12-31 | 北京自如信息科技有限公司 | Method and device for predicting quality of building object, electronic device and storage medium |
| CN114004138A (en) * | 2021-09-23 | 2022-02-01 | 杭萧钢构股份有限公司 | Building monitoring method and system based on big data artificial intelligence and storage medium |
-
2022
- 2022-07-28 CN CN202210895806.6A patent/CN115063040B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629144A (en) * | 2018-06-11 | 2018-10-09 | 湖北交投智能检测股份有限公司 | A kind of bridge health appraisal procedure |
| CN109099975A (en) * | 2018-09-29 | 2018-12-28 | 上海大学 | A kind of building structure health monitoring systems |
| CN109883474A (en) * | 2019-02-20 | 2019-06-14 | 吉林建筑大学 | Building health monitoring systems and monitoring method based on field monitoring |
| WO2020200847A1 (en) * | 2019-04-03 | 2020-10-08 | Peri Gmbh | Automatic prediction of the usability of concrete for at least one intended use at a construction site |
| US20220215250A1 (en) * | 2019-04-03 | 2022-07-07 | Peri Ag | Automatic prediction of the usability of concrete for at least one intended use at a construction site |
| CN110276542A (en) * | 2019-06-18 | 2019-09-24 | 合肥工业大学 | Complex equipment health state evaluation method based on ANP |
| CN111983459A (en) * | 2020-07-18 | 2020-11-24 | 武汉数值仿真技术研究院有限公司 | Health state testing and evaluating method based on vehicle lithium ion battery |
| CN111795978A (en) * | 2020-09-08 | 2020-10-20 | 湖南大学 | Steel bridge structure health state assessment method, device, equipment and storage medium |
| CN113237885A (en) * | 2021-04-22 | 2021-08-10 | 西安石油大学 | Building performance evaluation method based on structural health monitoring data |
| CN114004138A (en) * | 2021-09-23 | 2022-02-01 | 杭萧钢构股份有限公司 | Building monitoring method and system based on big data artificial intelligence and storage medium |
| CN113869774A (en) * | 2021-10-13 | 2021-12-31 | 北京自如信息科技有限公司 | Method and device for predicting quality of building object, electronic device and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| LI HUANG: "The sustainable development assessment of reservoir resettlement based on a BP neural network", 《INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH》 * |
| 王越等: "基于TFAHP的装配式建筑预制构件生产质量风险评估", 《黑龙江工程学院学报》 * |
| 郑海涛: "基于BP算法的钢结构建筑工业化建造施工质量评价体系研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 陈晓红: "面向智慧制造的工业数字孪生关键技术特性", 《科技导报》 * |
| 马崇森等: "基于BIM的建筑工程质量监督系统", 《改革与开放》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115063040B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ghosn et al. | Reliability-based performance indicators for structural members | |
| CN103116759B (en) | A kind of damnification recognition method being applicable to spatial mesh structure | |
| CN113900381B (en) | Steel structure remote health monitoring platform based on Internet of things and application method | |
| CN112884320B (en) | Foundation pit risk assessment method, device, equipment and medium based on entropy model | |
| CN103292762A (en) | Displacement monitoring method for judging dam stability | |
| CN105956216A (en) | Finite element model correction method for large-span steel bridge based on uniform temperature response monitoring value | |
| KR102098888B1 (en) | System and method for disaster prediction and analysis of structures, and a recording medium having computer readable program for executing the method | |
| KR102065435B1 (en) | Infrastructure health monitoring system and method | |
| CN114444180A (en) | Full life cycle parameter prediction and monitoring method and system for assembly type building structure | |
| CN114004631A (en) | Engineering cost control method and system based on BIM technology and computer equipment | |
| CN107861446A (en) | A kind of monitoring system and its application method for protecting building | |
| CN110162932A (en) | The calculation method of automatic monitoring slope stability based on finite element lattice | |
| Wang et al. | BIM-based structural health monitoring and early warning for heritage timber structures | |
| CN117629549A (en) | Bridge building health monitoring and safety early warning system | |
| CN104048843A (en) | Large-span bridge steel box beam damage early warning method based on GPS displacement monitoring | |
| CN115063040B (en) | Method and system for collaborative evaluation and prediction of house building structure health | |
| Oro et al. | Study of the influence of temperature and water level of the reservoir about the displacement of a concrete dam | |
| Sangiorgio et al. | User-reporting based decision support system for reinforced concrete building monitoring | |
| Limongelli et al. | Quantifying the value of monitoring for post-earthquake emergency management of bridges | |
| CN113536433A (en) | BIM platform-based dynamic escape route optimization system for evacuation after disaster of building | |
| CN107368938A (en) | Quantitative evaluation method for risk loss of single landslide | |
| KR20020021548A (en) | Remote Structure Measuring and Managing System Using Internet and Method Thereof | |
| CN115950485A (en) | Full-automatic intelligent monitoring method in tunnel | |
| JP4995161B2 (en) | Deterioration diagnosis system for wooden buildings | |
| Pan | Damage prediction of low-rise buildings under hurricane winds |
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 |