CN114239108B - Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things - Google Patents

Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things Download PDF

Info

Publication number
CN114239108B
CN114239108B CN202111551007.9A CN202111551007A CN114239108B CN 114239108 B CN114239108 B CN 114239108B CN 202111551007 A CN202111551007 A CN 202111551007A CN 114239108 B CN114239108 B CN 114239108B
Authority
CN
China
Prior art keywords
building
earthquake
monitoring
things
internet
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
CN202111551007.9A
Other languages
Chinese (zh)
Other versions
CN114239108A (en
Inventor
王健泽
陈尉唯
王文泽
戴靠山
衡明珠
徐安明
杨淳怡
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.)
Sichuan University
Original Assignee
Sichuan University
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 Sichuan University filed Critical Sichuan University
Priority to CN202111551007.9A priority Critical patent/CN114239108B/en
Publication of CN114239108A publication Critical patent/CN114239108A/en
Application granted granted Critical
Publication of CN114239108B publication Critical patent/CN114239108B/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]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Civil Engineering (AREA)
  • Computational Mathematics (AREA)
  • Structural Engineering (AREA)
  • Architecture (AREA)
  • Alarm Systems (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a city building group loss distribution calculation method after earthquake based on a monitoring Internet of things, belonging to the technical field of earthquake engineering; the method comprises the following steps: collecting the information of each single building in a target city before an earthquake occurs, establishing a data information base of an urban building group, and constructing a numerical simulation model of the urban building group; the method comprises the steps of bringing a monitoring system of public buildings in a target city into the Internet of things, and building a target city monitoring Internet of things; after an earthquake occurs, carrying out earthquake loss calculation simulation on the urban building group according to the actually measured earthquake waves; estimating the earthquake damage degree of the monitored building according to the damage conditions of the internal equipment and the home decoration of the building identified by the monitoring image; and estimating and correcting a numerical simulation result based on the damage degree inferred by the monitoring image, and evaluating the damage states of other unmonitored buildings to obtain the loss distribution of the urban building group after the earthquake. The method can realize the rapid estimation of the earthquake damage distribution of the urban building group after the earthquake occurs, and provides important reference for post-disaster rescue and emergency management.

Description

Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things
Technical Field
The invention relates to a method for calculating post-earthquake loss distribution of urban building groups, in particular to a method for calculating post-earthquake loss distribution of urban building groups based on a monitoring Internet of things, and belongs to the technical field of seismic engineering.
Background
The building is a main carrier of various activities in a city, and the guarantee of the earthquake resistance and disaster prevention capability of urban building groups is one of important research subjects in the field of earthquake engineering and is also the fundamental work for building toughness urban and rural areas. After earthquake, the damage distribution of the urban building group is rapidly evaluated, and important reference can be provided for rescue and emergency management after disaster.
For the space damage and economic loss simulation of urban building groups, the method mainly adopted at present is to establish a numerical model for the urban building groups and perform earthquake response analysis according to earthquake dynamic acceleration data monitored by a station. And estimating the economic loss condition of each single building according to the earthquake damage of the single buildings, thereby obtaining the space damage degree distribution and the economic loss condition of the urban building group under numerical simulation. However, the loss analysis result based on only the numerical simulation calculation has a certain limitation, for example, the verification of the numerical simulation calculation result cannot be guaranteed.
Disclosure of Invention
The purpose of the invention is: the method comprises the steps of rapidly judging the damage state of a non-structural component through the Internet of things and an image recognition method, summarizing and processing damage information through the Internet of things, correcting and updating the disaster simulation result of the urban building group, and improving the efficiency of urban building group earthquake damage prediction.
In order to achieve the purpose, the invention adopts the following technical scheme: the city building group loss distribution calculation method after earthquake based on the monitoring Internet of things comprises the following steps:
s1, before an earthquake occurs, collecting the information of each single building in the target city, and establishing a data information base of the target city building group; and establishing a finite element numerical model or a simplified Multi-degree-of-freedom (MDOF) mechanical model of each monomer building according to the information of each monomer building, and establishing and summarizing the numerical models of all the monomer buildings to form a numerical model of the urban building group.
S2, incorporating the monitoring system of the public buildings in the target city into the Internet of things, and building the target city monitoring Internet of things, wherein the monitoring system of each building is a single node in the Internet of things; and acquiring damage conditions of internal equipment, home decoration, structural members and non-structural members of the building, which are shot by the monitoring system of each public building in the earthquake occurrence process and after the earthquake occurs.
S3, after an earthquake occurs, substituting the earthquake waves into the city building group numerical model constructed in the step S1 by adopting a numerical simulation analysis means according to earthquake waves obtained by monitoring of the Chinese earthquake platform network to perform earthquake response analysis, and performing simulation calculation on earthquake loss of the city building group to obtain earthquake response calculation results of each single building, wherein the earthquake response calculation results comprise numerical simulation results R (simulated) of earthquake damage of public buildings including the monitoring Internet of things;
the method is characterized in that a machine learning K-means algorithm is adopted to perform cluster analysis on numerical simulation results of all buildings in the urban building group, seismic response and loss degree of the buildings are used as main characteristics, public buildings brought into the monitoring Internet of things must be used as limiting conditions in each classification, and building classification number and classification conditions are calculated in an optimized mode.
S4, according to the target city monitoring Internet of things set up in the step S2, an image recognition method is adopted, damage conditions of the non-structural members in the building are recognized through monitoring pictures after the earthquake occurs in the earthquake occurrence process, structural system earthquake response R (observed) corresponding to the placement positions of the non-structural members is obtained through inversion according to the vulnerability theory of the non-structural members in the earthquake engineering field, and earthquake response parameters of the structural system mainly comprise floor peak acceleration and interlayer displacement angles.
S5, obtaining a coefficient model between two seismic response results based on the monitoring image recognition means and the numerical simulation means respectively based on the destruction degree of the internal non-structural member of the public building recognized by the monitoring screen in the step S4 and the structural seismic response r (inverted) obtained by the inversion, and the seismic response calculation result r (simulated) of the public building obtained by the numerical simulation in the step S3, wherein the formula of the coefficient model is as follows:
Figure BDA0003417196500000031
wherein α is a correction coefficient for a numerical simulation result, r (updated) is a building seismic response obtained by a monitoring screen identification inversion, r (simulated) is a building seismic response obtained by a numerical simulation method, g (struct) is an influence factor related to a structural attribute of a public building incorporating the monitoring internet of things, and g (nsc) is an influence factor of a non-structural component type identified by the monitoring screen.
S6, updating and obtaining the earthquake response distribution probability obtained by numerical simulation by using Bayesian theory according to the public building earthquake response calculation result R (normalized) which is obtained by numerical simulation in the step S3 and is included in the monitoring Internet of things and the building internal damage state identified by the monitoring picture in the step S4, wherein the earthquake response distribution probability formula is as follows:
Figure BDA0003417196500000032
wherein P (Res ≧ x) represents the probability that the structural seismic response exceeds x, DS ob Seismic damage state, P (DS), representing autonomous identification of surveillance images ob ) Indicating the damage status of the building as DS ob The probability of (d); p (DS) ob | Res ≧ x) indicates that the building damage status is DS when the structural seismic response exceeds x ob The probability of (d); p (Res ≧ x | DS ob ) Representing the structural seismic damage state as DS ob The probability that the lower structure seismic response exceeds x.
S7, applying the coefficient model α of each public building obtained in the step S5 to other buildings in the same cluster to which each public building belongs in the step S3 to obtain a correction coefficient; applying the seismic response prior probability and the posterior probability model of each public building obtained in the step S6 to other buildings in the same cluster to which each public building belongs in the step S3 to obtain another correction coefficient;
and (3) carrying out secondary correction on the earthquake response numerical simulation result by adopting a Kriging algorithm according to the earthquake attenuation effect in the geographic space range of the target urban building group through the correction coefficient obtained by any one of the two modes, updating the earthquake response numerical simulation results of all buildings by utilizing all the building correction coefficients obtained by the Kriging algorithm, and finally obtaining the post-earthquake loss distribution of the target building group by combining the existing earthquake toughness evaluation rule.
In step S1, the individual building information mainly includes the construction age, the building height, the number of floors, the type of structural system, the floor area, and the standard floor area of each individual building.
In step S2, the public buildings incorporating the monitoring internet of things include schools, hospitals, commercial office buildings, commercial squares, and government office buildings, and the characteristics of the public buildings incorporating the monitoring internet of things need to be representative in the city building group to which the public buildings belong, and include structure type, building height, building location distribution, and building service life.
In the step S2, the internet of things is composed of all and part of monitoring systems of public buildings in the urban building group and is managed by the local emergency management department in a unified manner; the monitoring system of each building is a single node in the Internet of things, and the nodes of the Internet of things do not need to be independently arranged for earthquake disaster damage evaluation; in each individual public building, only the monitoring equipment arranged by daily operation and maintenance and safety precaution is needed, and a monitoring camera does not need to be separately and additionally configured.
In the step S4, the non-structural members included in the monitoring identification include floating furniture and equipment, a ceiling board and a filler wall, and when an earthquake occurs, the peak acceleration of the structural floor is estimated according to the sliding distance, the overturning probability and the shaking amplitude of the floating furniture and the equipment; estimating the peak acceleration of the structural floor according to the dropping plate damage degree of the suspended ceiling or the dropping plate rate of the suspended ceiling plate; and estimating the displacement angle between the inner layers of the structural plane according to the cracking degree of the filler wall and the glass curtain wall.
In step S7, the modified formula of the Kriging algorithm is as follows:
Figure BDA0003417196500000051
wherein n represents the number of public buildings incorporating the monitoring internet of things; s i Representing the geographical location of the ith public building; z(s) i ) A correction factor representing the ith public building seismic response; w is a i As a weight coefficient, through the ground of n public buildingsOptimally calculating and determining seismic response correction coefficient data;
Figure BDA0003417196500000052
and a quadratic correction factor representing the seismic response of any building not incorporating the monitoring internet.
In the step S7, a K-means cluster learning algorithm in the machine learning algorithm is adopted to perform rapid earthquake damage estimation on adjacent or similar attribute buildings of the monitored single public building, and after an earthquake occurs, the urban building group loss spatial distribution is rapidly updated.
The invention has the beneficial effects that:
1) compared with the means of site survey, satellite/unmanned aerial vehicle building appearance earthquake damage shooting and the like, the method for predicting the urban building group earthquake damage distribution through the Internet of things and monitoring picture image recognition has the advantages of wide monitoring range, low technical cost and strong timeliness; the method can realize quick estimation of earthquake damage distribution of urban building groups after the earthquake occurs, and provides important reference for rescue and emergency management after the earthquake occurs.
2) According to the invention, the disaster simulation result of the urban building group is corrected and updated by the Internet of things and the image recognition method, so that the accuracy of the simulation result is improved; the problem that the loss analysis result only based on numerical simulation calculation has deviation is avoided.
3) The method combines the internet of things and the image recognition technology to quickly judge the damage state of the non-structural member, and then the internet of things is used for summarizing and processing the damage information, so that the economic loss, the casualties and the like of the target urban building group are quickly estimated, and the efficiency of earthquake damage prediction of the urban building group is improved.
Drawings
FIG. 1 is a flow chart of a spatial distribution calculation method of the present invention;
FIG. 2 is a monitoring call zoning map in step 2 of the present invention;
FIG. 3 is a process diagram of the earthquake damage prediction method of the non-monitored area according to the present invention.
Detailed Description
The invention is further explained below with reference to the figures and the embodiments.
Example (b): as shown in fig. 1 to 3, the method for calculating the post-earthquake loss distribution of the urban building group based on the monitoring internet of things provided by the invention comprises the following steps:
s1, before an earthquake occurs, collecting the information of each single building in the target city, and establishing a data information base of the target city building group; and establishing a simplified Multi-degree-of-freedom (MDOF) mechanical model of each monomer building according to the information of each monomer building, and establishing and summarizing numerical models of all monomer buildings to form a numerical model of the urban building group.
The single building information mainly comprises the construction age, the building height, the floor number, the structure system type, the occupied area and the standard floor area of each single building.
S2, incorporating the monitoring system of the public buildings in the target city into the Internet of things, and building the target city monitoring Internet of things, wherein the monitoring system of each building is a single node in the Internet of things; and acquiring damage conditions of internal equipment, home decoration, structural members and non-structural members of the building, which are shot by the monitoring system of each public building, in the earthquake occurrence process and after the earthquake occurs.
Public buildings include schools, hospitals, commercial office buildings, commercial squares, government office buildings; the Internet of things is composed of all and part monitoring systems of public buildings in urban building groups and is uniformly managed by local emergency management departments; the monitoring system of each building is a single node in the Internet of things, and the nodes of the Internet of things do not need to be independently arranged for earthquake disaster damage evaluation; in each individual public building, only the monitoring equipment arranged by daily operation and maintenance and safety precaution is needed, and a monitoring camera does not need to be separately and additionally configured.
When public buildings incorporating the monitoring Internet of things are selected, the characteristics of structure type, building height, building space distribution and building service life need to be considered.
1) The structure type is as follows: the types of urban building structures at present can be divided into steel concrete, steel, brick concrete and other types, and according to the past earthquake damage experience, the earthquake resisting capability of buildings with different structural types in the earthquake is different. Under the condition of the same earthquake fortification intensity, the earthquake resistance of the reinforced concrete structure is stronger than that of other structure types, and when an earthquake occurs, the earthquake response of non-structural members in different building structures is greatly different. Therefore, public buildings with various structural types in the urban building group are selected.
2) Building height: with the development of society, the occupation ratio of high-rise buildings and super high-rise buildings in urban building groups is increasing day by day. Research shows that the floor height of the structure influences the floor response under the action of earthquake, and the floor peak acceleration amplification factor is obviously increased compared with the ground peak acceleration along with the increase of the floor height, so that the earthquake response of non-structural members in the building is directly influenced. Therefore, high-rise and medium-and-low-rise public buildings which incorporate the monitoring Internet of things in the urban building group are selected.
3) Building space distribution: public buildings brought into the Internet of things are prevented from being excessively concentrated, and the public buildings are uniformly and randomly distributed on the position distribution of a target urban building group as much as possible. An example of a public building that incorporates the internet of things for monitoring in a city building complex is shown in fig. 2.
4) And the service life of the building: with the development of urbanization promotion and urban updating, not only new buildings exist in urban building groups, but also old buildings have larger occupation ratio. Such buildings, due to their early age, have different design and use specifications from those of newly built buildings, which can lead to differences in seismic response of the non-structural elements within the building. Therefore, the monitoring internet of things also takes into account the building groups in the old urban area.
S3, after an earthquake occurs, substituting the earthquake waves into the city building group numerical model constructed in the step S1 to perform earthquake response analysis by adopting a numerical simulation analysis means according to earthquake waves obtained by monitoring of the Chinese earthquake table network, and performing simulation calculation on earthquake loss of the city building group to obtain earthquake response calculation results of each single building, wherein the earthquake response calculation results comprise numerical simulation results R (simulated) of earthquake damage of public buildings including the monitoring Internet of things;
the method is characterized in that a machine learning K-means algorithm is adopted to perform cluster analysis on numerical simulation results of all buildings in the urban building group, seismic response and loss degree of the buildings are used as main characteristics, public buildings brought into the monitoring Internet of things must be used as limiting conditions in each classification, and building classification number and classification conditions are calculated in an optimized mode.
S4, according to the target city monitoring Internet of things set up in the step S2, an image recognition method is adopted, damage conditions of the non-structural members in the building are recognized through monitoring pictures after the earthquake occurs in the earthquake occurrence process, structural system earthquake response R (observed) corresponding to the placement positions of the non-structural members is obtained through inversion according to the vulnerability theory of the non-structural members in the field of earthquake engineering, and earthquake response parameters of the structural system mainly comprise floor peak acceleration and displacement angles between structural planes.
The non-structural members have a plurality of classification modes according to parameters such as connection forms, response indexes, sensitivity and the like, and can be widely used in image recognition technology and can be divided into three categories of floating furniture and equipment, ceiling boards and filling walls, wherein the following are typical damage examples of the three categories of non-structural members:
1) the floating furniture and equipment refer to equipment which is directly placed on a floor or ground without being connected by a rivet, a bolt and other members, such as computers in commercial office buildings, medical equipment in hospitals, articles placed on home decoration counters and the like. The main motion responses of the floating furniture and the equipment in the earthquake are sliding, overturning, shaking and composite motion states, wherein the most common damage modes are that the equipment collides with structural members such as walls and the like due to sliding, the equipment collides with floors or the ground in the shaking process, or overturns due to overlarge shaking inclination angles. Relevant researches show that when an earthquake occurs, the sliding distance, the overturning probability and the shaking amplitude of the floating furniture and equipment are in positive correlation with the peak acceleration of the structural floor. Therefore, earthquake response and damage conditions of the structure can be judged by monitoring the acquired earthquake damage conditions of the floating furniture and the equipment, and the peak acceleration of the floor of the structure is estimated through the vulnerability theory.
2) The falling plate damage degree of the suspended ceiling or the falling plate rate of the suspended ceiling plate, namely the ratio of the number of the suspended ceiling plates falling off in the earthquake to the total number of the suspended ceiling plates of one continuous suspended ceiling is used as the quantitative index of the damage degree of the suspended ceiling. Therefore, the damage state of the suspended ceiling can be judged according to the falling condition of the suspended ceiling plate obtained by image recognition, and the peak floor acceleration is estimated through the vulnerability function of the suspended ceiling plate.
3) For the filler wall and the glass curtain wall, the inter-layer displacement angle of the structural surface can be judged according to the cracking degree obtained by image recognition.
S5, obtaining a coefficient model between two seismic response results based on the monitoring image recognition means and the numerical simulation means respectively based on the destruction degree of the internal non-structural member of the public building recognized by the monitoring screen in the step S4 and the structural seismic response r (inverted) obtained by the inversion, and the seismic response calculation result r (simulated) of the public building obtained by the numerical simulation in the step S3, wherein the formula of the coefficient model is as follows:
Figure BDA0003417196500000091
wherein α is a correction coefficient for a numerical simulation result, r (updated) is a building seismic response obtained by a monitoring screen identification inversion, r (simulated) is a building seismic response obtained by a numerical simulation method, g (struct) is an influence factor related to a structural attribute of a public building incorporating the monitoring internet of things, and g (nsc) is an influence factor of a non-structural component type identified by the monitoring screen.
S6, updating the earthquake response distribution probability obtained by numerical simulation according to the earthquake response calculation result r (weighted) of the public building including the monitoring internet of things obtained by numerical simulation in the step S3 and the internal damage state of the building identified by the monitoring screen in the step S4 by using bayes theory, wherein the earthquake response distribution probability has the following formula:
Figure BDA0003417196500000092
wherein, P (Res ≧ x) is shownProbability, DS, of structural seismic response exceeding x ob Seismic damage state, P (DS), representing autonomous identification of surveillance images ob ) Indicating the damage status of the building as DS ob The probability of (d); p (DS) ob | Res ≧ x) indicates that the building damage status is DS when the structural seismic response exceeds x ob The probability of (d); p (Res ≧ x | DS ob ) Representing the structural seismic damage state as DS ob The probability that the lower structure seismic response exceeds x.
S7, applying the coefficient model α of each public building obtained in the step S5 to other buildings in the same cluster to which each public building belongs in the step S3 to obtain a correction coefficient; applying the seismic response prior probability and the posterior probability model of each public building obtained in the step S6 to other buildings in the same cluster to which each public building belongs in the step S3 to obtain another correction coefficient;
the correction coefficients obtained by any one of the two modes are used for secondarily correcting the earthquake response numerical simulation result by adopting the Kriging algorithm according to the earthquake attenuation effect in the geographic space range of the target urban building group, and after the earthquake response numerical simulation results of all buildings are updated by using all the building correction coefficients obtained by the Kriging algorithm, the post-earthquake loss distribution of the target building group is finally obtained by combining the existing earthquake toughness evaluation rule;
the modified formula of the Kriging algorithm is as follows:
Figure BDA0003417196500000101
wherein n represents the number of public buildings incorporating the monitoring internet of things; s i Representing the geographic location of the ith public building; z(s) i ) A correction factor representing the ith public building seismic response; w is a i The weight coefficient is determined by the optimized calculation of the seismic response correction coefficient data of n public buildings;
Figure BDA0003417196500000102
representing any earthquakes not incorporated into the monitored internet structureThe second order correction factor of the response.
A K-means clustering learning algorithm based on a machine learning algorithm is used for quickly estimating the earthquake damage of adjacent or similar attribute buildings of a monitored single public building, and after an earthquake occurs, the loss space distribution of an urban building group is quickly updated by combining a correction coefficient model obtained by a similarity relation or Bayesian theory and a Kriging method, so that the efficiency of earthquake damage prediction of the urban building group is improved.
The earthquake response of the updated urban building group obtained by the steps can be quickly estimated according to the evaluation standard of earthquake resistance toughness of buildings in GB/T38591-2020, and the economic loss, casualties and the like of the target urban building group.
Compared with the means of site survey, satellite/unmanned aerial vehicle building appearance earthquake damage shooting and the like, the method for predicting the urban building group earthquake damage distribution through the Internet of things and monitoring picture image recognition has the advantages of wide monitoring range, low technical cost and strong timeliness; the method can realize quick estimation of earthquake damage distribution of urban building groups after the earthquake occurs, and provides important reference for rescue and emergency management after the earthquake occurs.
By the aid of the Internet of things and an image recognition method, the disaster simulation result of the urban building group is corrected and updated, and accuracy of the simulation result is improved; the problem that the loss analysis result only based on numerical simulation calculation has deviation is avoided.
The damage state of the non-structural component is rapidly judged by combining the internet of things and an image recognition technology, damage information is summarized and processed by the internet of things, economic loss, casualties and the like of a target urban building group are rapidly estimated, and the efficiency of earthquake damage prediction of the urban building group is improved.
The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (7)

1. The city building group loss distribution calculation method after earthquake based on the monitoring Internet of things is characterized by comprising the following steps: the method comprises the following steps:
s1, before an earthquake occurs, collecting the information of each single building in the target city, and establishing a data information base of the target city building group; establishing a finite element numerical model or a simplified Multi-degree-of-freedom (MDOF) mechanical model of each monomer building according to the information of each monomer building, and establishing and summarizing the numerical models of all the monomer buildings to form a city building group numerical model;
s2, incorporating the monitoring system of the public buildings in the target city into the Internet of things, and building the target city monitoring Internet of things, wherein the monitoring system of each building is a single node in the Internet of things; acquiring damage conditions of internal equipment, home decoration, structural members and non-structural members of the building, which are shot by a monitoring system of each public building in the earthquake occurrence process and after the earthquake occurs;
s3, after an earthquake occurs, substituting the earthquake waves into the city building group numerical model constructed in the step S1 to perform earthquake response analysis by adopting a numerical simulation analysis means according to earthquake waves obtained by monitoring of the Chinese earthquake table network, and performing simulation calculation on earthquake loss of the city building group to obtain earthquake response calculation results of each single building, wherein the earthquake response calculation results include earthquake response simulation calculation results R (simulated) of earthquake damage of public buildings including the monitoring Internet of things;
performing clustering analysis on numerical simulation results of all buildings in the urban building group by adopting a machine learning K-means algorithm, taking seismic response and loss degree of the buildings as main characteristics, taking each classification of public buildings brought into the monitoring Internet of things as a limiting condition, and optimally calculating the classification number and classification condition of the buildings;
s4, identifying the damage condition of the non-structural member in the building by using a monitoring picture after the earthquake occurs in the earthquake occurrence process and an image identification method according to the target city monitoring Internet of things set up in the step S2, and obtaining a structural earthquake response R (observed) corresponding to the placement position of the non-structural member through inversion according to the vulnerability theory of the non-structural member in the earthquake engineering field, wherein the earthquake response parameters of the structural system mainly comprise floor peak acceleration and interlayer displacement angle;
s5, obtaining a coefficient model between two seismic response results based on the monitoring image recognition means and the numerical simulation means, based on the destruction degree of the internal non-structural member of the public building recognized by the monitoring screen in the step S4 and the structural seismic response r (inverted) obtained by the inversion, and the seismic response simulation calculation result r (simulated) of the public building obtained by the numerical simulation in the step S3, wherein the formula of the coefficient model is as follows:
Figure FDA0003770871800000021
wherein α is a correction coefficient for a numerical simulation result, r (updated) is a public building seismic response obtained by identification and inversion of a monitoring screen, r (multiplied) is a public building seismic response obtained by a numerical simulation mode, g (struct) is an influence factor related to a structural attribute of a public building incorporating the monitoring internet of things, and g (nsc) is an influence factor of a non-structural component type identified by the monitoring screen;
s6, updating and obtaining the earthquake response distribution probability obtained by numerical simulation by using Bayesian theory according to the earthquake response simulation calculation result R (simulated) of the public building including the monitoring Internet of things obtained by numerical simulation in the step S3 and the damage state in the building identified by the monitoring picture in the step S4, wherein the earthquake response probability distribution model is as follows:
Figure FDA0003770871800000022
wherein P (Res ≧ x) denotes the prior probability distribution, DS, of the public building's structural seismic response exceeding x ob Seismic damage state, P (DS), representing autonomous identification of surveillance images ob ) Indicating the damage status of the building as DS ob The probability of (d); p (DS) ob | Res ≧ x denotes the building damage status DS when the structural seismic response exceeds x ob The probability of (d); p (Res ≧ x | DS ob ) Representing structural seismic damage state as DS ob A posterior probability distribution of lower structure seismic response over x;
s7, applying the coefficient model α of each public building obtained in the step S5 to other buildings in the same cluster to which each public building belongs in the step S3 to obtain a correction coefficient; the seismic response prior probability model P (Res ≧ x) and the posterior probability model P (Res ≧ x | DS) of each public building obtained in the step S6 are combined ob ) Applying the correction coefficient to other buildings in the same cluster to which each public building belongs in the step S3 to obtain another correction coefficient;
and (3) carrying out secondary correction on the earthquake response numerical simulation result by adopting a Kriging algorithm according to the earthquake attenuation effect in the geographic space range of the target urban building group through the correction coefficient obtained by any one of the two modes, updating the earthquake response numerical simulation results of all buildings by utilizing all the building correction coefficients obtained by the Kriging algorithm, and finally obtaining the post-earthquake loss distribution of the target building group by combining the existing earthquake toughness evaluation rule.
2. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things according to claim 1, characterized in that: in step S1, the individual building information mainly includes the construction age, the building height, the number of floors, the type of structural system, the floor area, and the standard floor area of each individual building.
3. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things according to claim 1, characterized in that: in step S2, the public buildings incorporating the monitoring internet of things include schools, hospitals, commercial office buildings, commercial squares, and government office buildings, and the characteristics of the public buildings incorporating the monitoring internet of things need to be representative in the city building group to which the public buildings belong, and include structure type, building height, building location distribution, and building service life.
4. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things as claimed in claim 1, wherein: in step S2, the internet of things is composed of all and part of monitoring systems of public buildings in the urban building group and is managed by local emergency management departments in a unified manner; the monitoring system of each building is a single node in the Internet of things, and the nodes of the Internet of things do not need to be independently arranged for earthquake disaster damage evaluation; in each individual public building, only the monitoring equipment arranged by daily operation and maintenance and safety precaution is needed, and a monitoring camera does not need to be separately and additionally configured.
5. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things according to claim 1, characterized in that: in the step S4, the non-structural members included in the monitoring identification include floating furniture and equipment, a ceiling board and a filler wall, and when an earthquake occurs, the peak acceleration of the structural floor is estimated according to the sliding distance, the overturning probability and the shaking amplitude of the floating furniture and the equipment; estimating the peak acceleration of the structural floor according to the dropping plate damage degree of the suspended ceiling or the dropping plate rate of the suspended ceiling plate; and estimating the displacement angle between the inner layers of the structural plane according to the cracking degree of the filler wall and the glass curtain wall.
6. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things according to claim 1, characterized in that: in step S7, the modified formula of the Kriging algorithm is as follows:
Figure FDA0003770871800000041
wherein n represents the number of public buildings incorporating the monitoring internet of things; s i Representing the geographical location of the ith public building; z(s) i ) A correction factor representing the ith public building seismic response; w is a i The weight coefficient is determined by the optimized calculation of the seismic response correction coefficient data of n public buildings;
Figure FDA0003770871800000042
and a quadratic correction factor representing the seismic response of any building not incorporating the monitoring internet.
7. The city building group post-earthquake loss distribution calculation method based on the monitoring Internet of things according to claim 1, characterized in that: in the step S7, a K-means cluster learning algorithm in the machine learning algorithm is adopted to perform rapid earthquake damage estimation on adjacent or similar attribute buildings of the monitored single public building, and after an earthquake occurs, the urban building group loss spatial distribution is rapidly updated.
CN202111551007.9A 2021-12-17 2021-12-17 Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things Active CN114239108B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111551007.9A CN114239108B (en) 2021-12-17 2021-12-17 Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111551007.9A CN114239108B (en) 2021-12-17 2021-12-17 Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things

Publications (2)

Publication Number Publication Date
CN114239108A CN114239108A (en) 2022-03-25
CN114239108B true CN114239108B (en) 2022-09-13

Family

ID=80758145

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111551007.9A Active CN114239108B (en) 2021-12-17 2021-12-17 Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things

Country Status (1)

Country Link
CN (1) CN114239108B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114741758B (en) * 2022-04-12 2024-04-05 大连理工大学 Building earthquake-resistant toughness preliminary design method and system based on machine learning
CN114792020B (en) * 2022-04-12 2024-05-03 大连理工大学 Quick evaluation method and system for building anti-seismic toughness based on machine learning
CN115148005A (en) * 2022-05-24 2022-10-04 贝壳找房(北京)科技有限公司 Central control panel for earthquake early warning and earthquake early warning method
CN115049924B (en) * 2022-06-06 2023-04-14 四川大学 Building earthquake damage assessment method based on non-structural member damage identification under video monitoring
CN116523663B (en) * 2023-06-29 2023-09-01 北京科技大学 Method and device for determining urban building group wind disaster insurance premium based on physical model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104240034A (en) * 2014-09-23 2014-12-24 北京师范大学 Method for quickly evaluating economic losses generated by landslides caused by earthquakes
JP2018100494A (en) * 2016-12-19 2018-06-28 株式会社益田建設 Building having earthquake damage evaluation function

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110046819B (en) * 2019-04-16 2021-06-18 韧科(浙江)数据技术有限公司 Post-disaster coupling recovery analysis method for urban infrastructure system
CN112085922A (en) * 2020-09-01 2020-12-15 东莞理工学院 Intelligent early warning and monitoring method for earthquake damage of building
CN214707768U (en) * 2021-03-25 2021-11-12 兰州工业学院 High-rise building SHM system based on LORA + BIM technology
CN113435091B (en) * 2021-06-29 2022-11-11 哈尔滨工业大学 Method for rapidly evaluating earthquake damage of urban building group bridge group

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104240034A (en) * 2014-09-23 2014-12-24 北京师范大学 Method for quickly evaluating economic losses generated by landslides caused by earthquakes
JP2018100494A (en) * 2016-12-19 2018-06-28 株式会社益田建設 Building having earthquake damage evaluation function

Also Published As

Publication number Publication date
CN114239108A (en) 2022-03-25

Similar Documents

Publication Publication Date Title
CN114239108B (en) Urban building group loss distribution calculation method after earthquake based on monitoring Internet of things
Michel et al. Seismic vulnerability assessment to slight damage based on experimental modal parameters
Crowley et al. A comparison of seismic risk maps for Italy
Santa María et al. Development of national and local exposure models of residential structures in Chile
CN108984932B (en) Building structure characteristic rapid extraction method and corresponding loss evaluation calculation method
Nicodemo et al. Modelling exposure and vulnerability from post-earthquake survey data with risk-oriented taxonomies: AeDES form, GEM taxonomy and EMS-98 typologies
CN115017591A (en) Building structure group earthquake-resistant performance evaluation method
CN114881511A (en) Flood disaster-oriented community disaster-prevention toughness evaluation method
Kechidi et al. Seismic risk assessment of cold-formed steel shear wall systems
KR102143805B1 (en) Device for Predicting Fragility of Structures due to Disasters and the Method
Zhang et al. Developing GIS-based earthquake loss model: a case study of Baqiao District, China
Sangaki et al. Probabilistic integrated framework and models compatible with the reliability methods for seismic resilience assessment of structures
CN114792020A (en) Method and system for quickly evaluating building earthquake resistance toughness based on machine learning
CN113536433A (en) BIM platform-based dynamic escape route optimization system for evacuation after disaster of building
Bertero et al. Seismic Hazard in Buenos Aires, Argentina, considering the influence of site effects and long-distance earthquakes
CN114037283A (en) Fire dynamic risk assessment method for commercial complex
CN111339483B (en) GNSS image generation method based on trend-removing cross-correlation analysis
Donà et al. Derivation of mechanical fragility curves for macro-typologies of Italian masonry buildings
CN113449953A (en) Assembly type building construction safety assessment method
CN117350974A (en) Engineering quality determining method, device, equipment and medium
Morais et al. Cyclic behaviour, dynamic analysis and seismic vulnerability of historical building archetypes in Hungary
Shahbazi et al. Loss modeling for 2017 Sarpol-e Zahab Earthquake
CN116703197A (en) Method and system suitable for rapid collaborative evaluation of earthquake disasters in black box period
CN109784602A (en) A kind of disaster-ridden kind of coupling physical vulnerability assessment method based on PTVA model
CN115049924A (en) Building earthquake damage assessment method based on non-structural component damage identification under video monitoring

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