CN115017591A - Building structure group earthquake-resistant performance evaluation method - Google Patents

Building structure group earthquake-resistant performance evaluation method Download PDF

Info

Publication number
CN115017591A
CN115017591A CN202210697162.XA CN202210697162A CN115017591A CN 115017591 A CN115017591 A CN 115017591A CN 202210697162 A CN202210697162 A CN 202210697162A CN 115017591 A CN115017591 A CN 115017591A
Authority
CN
China
Prior art keywords
building
earthquake
seismic
target area
model
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.)
Pending
Application number
CN202210697162.XA
Other languages
Chinese (zh)
Inventor
马亚飞
何羽
王磊
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.)
Changsha University of Science and Technology
Original Assignee
Changsha University of Science and Technology
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 Changsha University of Science and Technology filed Critical Changsha University of Science and Technology
Priority to CN202210697162.XA priority Critical patent/CN115017591A/en
Publication of CN115017591A publication Critical patent/CN115017591A/en
Pending legal-status Critical Current

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
    • E—FIXED CONSTRUCTIONS
    • E04—BUILDING
    • E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
    • E04H9/00—Buildings, groups of buildings or shelters adapted to withstand or provide protection against abnormal external influences, e.g. war-like action, earthquake or extreme climate
    • E04H9/02—Buildings, groups of buildings or shelters adapted to withstand or provide protection against abnormal external influences, e.g. war-like action, earthquake or extreme climate withstanding earthquake or sinking of ground
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/048—Fuzzy inferencing
    • 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
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Architecture (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Operations Research (AREA)
  • Environmental & Geological Engineering (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Emergency Management (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Civil Engineering (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Structural Engineering (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Analysis (AREA)
  • Health & Medical Sciences (AREA)

Abstract

The invention discloses a building structure group anti-seismic performance evaluation method, which comprises the steps of obtaining structural geometric information through a remote sensing measurement technology, inputting an appearance picture of a building into a structure type identification model, and identifying the structure type of the building; converting the adjustable information into hidden information inside the structure through fuzzy reasoning; generating earthquake motion according to the field category, and constructing an earthquake motion field model of the target area; and carrying out seismic response analysis on the monomer buildings in the target area, inputting the obtained seismic response into a trained maximum interlayer displacement angle prediction model, predicting the maximum interlayer displacement angle of each monomer building, and then evaluating the structural damage grade by combining the monomer building damage indexes to finally realize the seismic damage distribution prediction of the building structure group in the target area. The method can predict the earthquake damage distribution of the building group before the earthquake occurs, so that the structure reinforcement decision can be made in time to improve the earthquake resistance of important buildings, and secondary disasters caused by the earthquake can be reduced to the maximum extent.

Description

Building structure group earthquake-resistant performance evaluation method
Technical Field
The invention relates to the field of structural seismic safety assessment, in particular to a method for assessing seismic performance of building structure groups.
Background
With the acceleration of the urbanization process, the population and wealth of China are rapidly concentrated into cities, the urban building group scale is continuously enlarged, the structural form is increasingly complex, and the functional coupling is increasingly tight. However, with the increase of service life, the problem of the degradation of the existing structure performance under the adverse environment gradually appears, and the structure seismic performance is remarkably reduced. Once an earthquake occurs, serious damage to urban building groups, serious casualties and property loss can be caused. The existing earthquake-resistant safety assessment technology has the problems of single monitoring data, delayed assessment and the like, and urban disaster risks cannot be assessed in real time. If the earthquake damage distribution of a building group can be predicted before an earthquake occurs, a structure reinforcement decision is made in time to improve the earthquake resistance of an important building structure, and secondary disasters caused by the earthquake can be reduced to the maximum extent.
The intelligent and efficient acquisition of the structural information is the key for carrying out earthquake damage distribution prediction of the building group, the structural types of the building group in the region are various and the number of the building group is large, the traditional detection mainly takes manpower as the main part, the consumption of manpower and material resources is high, the working efficiency is low, and the detection precision is difficult to guarantee. In recent years, remote sensing image technology has been widely applied to geographic information acquisition, has the advantages of wide coverage, strong timeliness, high identification degree and the like, and can be used for acquiring structural appearance information. However, the remote sensing image is difficult to accurately judge the structure type, and the determination of the structure type is still limited to subjective judgment. Along with the rapid development of intelligent mobile equipment and artificial intelligence technology, the inventor finds that if images can be collected through intelligent sensing and a database is constructed, and training is carried out by adopting target detection deep learning, the efficiency and the accuracy of structure type prediction can be obviously improved, and the operation is simple and convenient.
The inventor finds that compared with the appearance information of the building structure in the region, hidden information such as the structure and materials in the structure is difficult to directly obtain due to long construction time, lost drawings and the like. The fuzzy theory can carry out fuzzy reasoning on indirect information by selecting key information which is easy to obtain and setting a fuzzy rule according to expert experience. However, how to infer hidden information such as anti-seismic structure in the structure based on the fuzzy theory needs to be further explored. In addition, compared with single buildings, the earthquake motions borne by different building units in the area are different obviously due to different positions, field conditions and the like. Therefore, how to consider the influences of spatial position, soil layer conditions and the like, and integrate multi-source data such as image information, fuzzy information, sensing monitoring and the like to perform safety risk assessment on the structure group in the region becomes a major problem to be solved urgently in intelligent operation and maintenance of the urban building group.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the building structure group anti-seismic performance evaluation method, which realizes the evaluation of the anti-seismic performance of the building structure group in the area by considering the influence of the spatial position and the soil layer condition and integrating multi-source data such as image information, fuzzy information, sensing monitoring and the like.
In order to achieve the purpose, the invention adopts the following technical scheme:
a building structure group earthquake-resistant performance evaluation method comprises the following steps:
acquiring an appearance picture of each monomer building in a target area, and respectively inputting the appearance picture into a structure type recognition model constructed based on a convolutional neural network for structure type recognition;
obtaining a remote sensing image of each single building and processing the remote sensing image to obtain the structural geometric dimension of each single building;
acquiring adjustable research information of each single building, and obtaining the internal hidden information of the structure of each single building based on a fuzzy reasoning method by combining the structure type of each single building;
building a building structure group simulation model based on the structure type, the structure geometric dimension and the structure internal hidden information of each single building;
determining a bedrock seismic power spectrum suitable for a target area according to the field category and the seismic intensity information, filtering a transfer function through a soil layer to obtain a surface seismic power spectrum, and further establishing a seismic dynamic field model of the target area;
building structure group earthquake dynamics models are built by combining the building structure group simulation models and the target area earthquake dynamic field models, earthquake response of each single building is calculated through earthquake response analysis, the earthquake response is input into a maximum interlayer displacement angle prediction model built based on a long-time memory network, the maximum interlayer displacement angle of each single building is obtained, and earthquake damage distribution of the building structure groups is evaluated by combining single building damage indexes.
Further, the structure type identification model is constructed on the basis of a Yolov5 neural network.
Further, the fuzzy inference method comprises the following steps:
taking the construction age as adjustable research information, and taking the material strength, construction measures and reinforcement conditions as hidden information in the structure;
and establishing a double-input three-output fuzzy inference model with the construction age and the structure type as input and the material strength, the construction measures and the reinforcement condition as output for fuzzy inference.
Furthermore, the construction time domain is [ A, B ], the unit is year, the fuzzy linguistic variables are 'early' and 'late', the membership function is bell-shaped, and the year B is greater than the year A; the structure type domain is [1, 8], and the fuzzy linguistic variables are: the masonry structure, the frame structure, the shear wall structure, the frame-shear wall structure, the frame support structure, the cylinder structure, the frame cylinder structure and the large span structure are of eight types, and the membership function of the cylinder structure, the frame cylinder structure and the large span structure is triangular; the material strength discourse domain is [1, 5], and the fuzzy linguistic variables are: the low type, the middle type, the lower type, the middle type and the high type, and the membership function is a triangle; the construction measure domain is [0, 1], the fuzzy linguistic variable is 'present' and 'absent', and the membership function is a trapezoid; the reinforcement measure domain is [0, 1], the fuzzy linguistic variable is 'reinforcement not' and 'reinforcement', and the membership function is trapezoid.
Further, the target area seismic motion field model is established by the following method:
and generating a bedrock seismic power spectrum of the target area according to the field type and the seismic intensity information, considering the transfer effect of seismic motion from bedrock to earth surface, and filtering a transfer function according to a soil layer to obtain the earth surface power spectrum of each target point in the target area so as to generate a seismic motion time course corresponding to each target point.
Further, the surface power spectrum is:
S g (ω)＝|H n (ω)| 2 ×S n-1 (ω)＝|H n (ω)| 2 ×|H n-1 (ω)| 2 ×S n-2 (ω)＝…＝|H g (ω)| 2 ×S r (ω)
Figure BDA0003703115380000031
in the formula, ω represents frequency; s g (ω) is the surface seismic power spectrum; s r (ω) is the seismic power spectrum with the bedrock; h i (ω) is the soil layer filtration transfer function for each layer of soil, expressed as:
Figure BDA0003703115380000032
in the formula, xi i Represents the energy transfer dissipation damping ratio, gamma, of the i-th layer of soil i Is the reflection coefficient, tau, at the layer boundary of the i-th layer soil i The propagation time of the seismic waves in the ith layer of soil is obtained; gamma ray i And τ i Respectively expressed as:
Figure BDA0003703115380000033
τ i ＝h i /υ i
in the formula, ρ i Denotes the density, upsilon, of the i-th layer of soil i Representing the propagation wave velocity h of seismic waves in the i-th layer of soil i The thickness of the ith soil layer is shown.
Further, the maximum interlayer displacement angle prediction model is constructed based on a long-time and short-time memory network model, seismic response is used as input, the maximum interlayer displacement angle is used as output, and a particle swarm optimization is adopted in the training process to optimize model parameters.
Further, the evaluation of the distribution of earthquake damage of the building structure group by combining the single building damage indexes comprises the following steps:
simulating the situation that different-intensity earthquakes occur in a target area based on the earthquake dynamics model of the building structure group to obtain the maximum interlayer displacement angle of each monomer building under different earthquake intensities;
comparing the maximum interlayer displacement angle of each monomer building with an interlayer displacement limit value specified by a monomer building damage index, and grading each monomer building to be one of intact, basically intact, slightly damaged, moderately damaged, severely damaged and collapsed;
and calibrating each single building according to grades to obtain the earthquake damage distribution of building structure groups in different earthquake intensities of the target area.
The invention provides an earthquake resistance evaluation method for a building structure group, which comprises the following parts of structure information acquisition, fuzzy information reasoning, earthquake dynamic field simulation and earthquake damage evaluation, wherein the structure geometric information is acquired through a remote sensing measurement technology, and the structure type of a building is identified based on a building appearance picture by utilizing a trained structure type identification model; converting the adjustable information into hidden information inside the structure through fuzzy reasoning; generating earthquake motion according to the field type, and constructing an earthquake motion field model of the target area by considering the single building position and soil layer information of the target area; and carrying out seismic response analysis on the monomer buildings in the target area, inputting the obtained seismic response into a trained maximum interlayer displacement angle prediction model, predicting the maximum interlayer displacement angle of each monomer building, and then evaluating the structural damage grade by combining the monomer building damage indexes to finally realize the seismic damage distribution prediction of the building structure group in the target area. The method can be used for predicting the earthquake damage distribution of the building group before the earthquake occurs, so that the structure reinforcement decision can be made in time according to the earthquake damage distribution to improve the earthquake resistance of important buildings, and secondary disasters caused by the earthquake can be reduced to the maximum extent. The prediction method is reasonable, high in calculation efficiency and strong in popularization, and can be widely applied to intelligent evaluation of earthquake-resistant safety of urban building structure groups.
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, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for evaluating earthquake resistance of a building structure group according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It should be apparent that the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention discloses a method for evaluating seismic performance of a building structure group, including:
s1: and acquiring the appearance picture of each single building in the target area, and respectively inputting the appearance picture into a structure type recognition model constructed based on the convolutional neural network for structure type recognition.
In this embodiment, the structural types include eight classic architectural structural types: masonry structure, frame structure, shear wall structure, frame-shear wall structure, frame support structure, barrel structure, frame barrel structure and large span structure. A large number of monomer building appearance pictures containing the eight classic building structure types and a component training set are collected in advance, the appearance pictures are used as input, the corresponding structure types are used as output, based on the training set, a migration learning method is adopted to carry out freezing training on the Yolov5 neural network model parameters, and a structure type recognition model is obtained after training. The appearance picture of the single building can be obtained by shooting through a mobile phone or a camera and other shooting means.
S2: and acquiring a remote sensing image of each single building and processing the remote sensing image to obtain the structural geometric dimension of each single building. The satellite remote sensing image determines the building appearance size through a proportionality coefficient, and specifically comprises the following steps:
Figure BDA0003703115380000041
s3: and acquiring adjustable research information of each single building, and obtaining the internal hidden information of the structure of each single building based on a fuzzy reasoning method by combining the structure type of each single building.
Specifically, the construction age is used as adjustable information, and the material strength, construction measures and reinforcement conditions are used as hidden information inside the structure. Therefore, a double-input three-output fuzzy reasoning model which takes the construction age and the structure type as input and takes the material strength, the construction measures and the reinforcement situation as output is established for fuzzy reasoning, and the conversion of fuzzy information to accurate numerical values is realized through fuzzy rules.
In this embodiment, the construction time domain is [ a, B ], the unit is year, the fuzzy linguistic variables are "early" and "late", the membership function is bell-shaped, it should be noted that the years a and B can be selected according to actual needs, for example, a can be 1960, 1965, 1970, etc., B can be 2020, 2021, even the years of a certain stage in the future; the structure type discourse domain is [1, 8], and the fuzzy linguistic variables are: the masonry structure, the frame structure, the shear wall structure, the frame-shear wall structure, the frame support structure, the cylinder structure, the frame cylinder structure and the large span structure are of eight types, and the membership function of the cylinder structure, the frame cylinder structure and the large span structure is triangular; the material strength discourse domain is [1, 5], and the fuzzy linguistic variables are: the low type, the middle type, the lower type, the middle type and the high type, and the membership function is a triangle; the construction measure domain is [0, 1], the fuzzy linguistic variable is 'present' and 'absent', and the membership function is a trapezoid; the reinforcement measure domain is [0, 1], the fuzzy linguistic variable is 'reinforcement not' and 'reinforcement', and the membership function is trapezoid.
S4: and constructing a building structure group simulation model based on the structure type, the structure geometric dimension and the structure internal hidden information of each single building.
S5: determining a bedrock seismic power spectrum suitable for the target area according to the field category and the seismic intensity information, filtering a transfer function through a soil layer to obtain a surface seismic power spectrum, and further establishing a seismic dynamic field model of the target area.
Specifically, firstly, a path effect function and a soil layer filtering transfer function are established according to the field category of a target area, and a seismic source power spectrum is generated according to seismic intensity information; then, obtaining a bedrock seismic power spectrum of the target area according to the seismic source power spectrum and the path effect function; and finally, obtaining the earth surface seismic power spectrum of each target point in the target area according to the bedrock seismic power spectrum and the soil layer filtering transfer function, and further generating the seismic motion time course corresponding to each target point.
Wherein, the surface seismic power spectrum can be expressed as:
S g (ω)＝|H n (ω)| 2 ×S n-1 (ω)＝|H n (ω)| 2 ×|H n-1 (ω)| 2 ×S n-2 (ω)＝…＝|H g (ω)| 2 ×S r (ω)
Figure BDA0003703115380000051
in the formula, ω represents frequency; s. the g (ω) is the surface seismic power spectrum; s r (ω) is the seismic power spectrum with the bedrock; h i (ω) is the soil layer filtration transfer function for each layer of soil, expressed as:
Figure BDA0003703115380000052
in the formula, xi i Represents the energy transfer dissipation damping ratio, gamma, of the i-th layer of soil i Is the reflection coefficient, tau, at the layer boundary of the i-th layer soil i The propagation time of the seismic waves in the ith layer of soil is obtained; gamma ray i And τ i Respectively expressed as:
Figure BDA0003703115380000053
τ i ＝h i /υ i
in the formula, ρ i The density of the i-th soil layer is represented, i is 1, …, n is the foundation soil when i is 1, n is the total number of soil layers, upsilon is i Representing the propagation wave velocity h of seismic waves in the i-th layer of soil i The thickness of the ith soil layer is shown.
S6: building structure group earthquake dynamics models are built by combining the building structure group simulation models and the target area earthquake dynamic field models, earthquake response of each single building is calculated through earthquake response analysis, the earthquake response is input into a maximum interlayer displacement angle prediction model built based on a long-time memory network, the maximum interlayer displacement angle of each single building is obtained, and earthquake damage distribution of the building structure groups is evaluated by combining single building damage indexes.
Specifically, in this embodiment, the seismic response is an acceleration response, acceleration responses of different individual buildings in the area are obtained by a seismic acceleration time-course analysis method, and the structural interlayer displacement angle θ can be calculated by the following formula:
Figure BDA0003703115380000061
in the formula, Δ u is the maximum horizontal displacement, and h is the layer height. The seismic response analysis method for calculating the seismic response and the maximum interlayer displacement angle is the prior art, and is not described herein again. The acceleration response and the corresponding maximum interlayer displacement angle are calculated, so that a training set for a maximum interlayer displacement angle prediction model can be established, and the maximum interlayer displacement angle can be obtained directly through the acquired acceleration response.
The maximum interlayer displacement angle prediction model is constructed based on a long-time and short-time memory network model, acceleration response is used as input, the maximum interlayer displacement angle is used as output, and prediction of the maximum interlayer displacement angle is achieved. In the process of training to obtain the maximum interlayer displacement angle prediction model, parameters such as the learning rate, the sequence length, the batch size and the like of the long-time and short-time memory network model are mainly optimized by adopting a particle swarm algorithm, and then the optimal model parameters are determined according to the fitness function.
It should be noted that, in other embodiments, step S6 may also directly calculate the seismic response and the maximum interlayer displacement angle of each single building through seismic response analysis, and then directly evaluate the distribution of earthquake damage of the building structure group according to the maximum interlayer displacement angle of each single building and the damage index of the single building.
In addition, the model established based on the method can be used for predicting the distribution of the earthquake damage of the building structure group in the target area in real time, namely, the acceleration sensor is installed on the building structure group in the target area to realize the real-time monitoring of acceleration response, then the acceleration response is input into the prediction model of the maximum interlayer displacement angle to predict the maximum interlayer displacement angle, and then the distribution of the earthquake damage of the building structure group is evaluated by combining the single building damage indexes.
Wherein, combine monomer building destruction index to carry out the aassessment to building structure crowd earthquake damage distribution, include:
simulating the situation that different-intensity earthquakes (including frequent and rare earthquakes) occur in a target area based on the building structure group earthquake dynamics model to obtain the maximum interlayer displacement angle of each monomer building under different earthquake intensities;
comparing the maximum interlayer displacement angle of each monomer building with an interlayer displacement limit value specified by a monomer building damage index, and grading each monomer building to be one of intact, basically intact, slightly damaged, moderately damaged, severely damaged and collapsed;
and calibrating each single building according to grades to obtain the earthquake damage distribution of building structure groups in different earthquake intensities of the target area.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The earthquake resistance evaluation scheme of the building structure group provided by the invention comprises four parts, namely structure information acquisition, fuzzy information reasoning, earthquake dynamic field simulation and earthquake damage evaluation. Acquiring structural geometric information by a remote sensing measurement technology, acquiring typical structure type pictures by a mobile phone or a camera and the like, constructing a database, and identifying the building structure type by adopting a multiple improved Yolov5 and a transfer learning training model; establishing membership functions of the adjustable research information and the hidden information, and converting the adjustable research information into the hidden information through fuzzy reasoning; generating earthquake motion according to the field type, and constructing a structure group space earthquake motion field model by considering different types of monomer building positions and soil layer information in the area; the method comprises the steps of analyzing earthquake response of single buildings in a target area, constructing an acceleration response and maximum interlayer displacement angle matching database, training data based on a long-time and short-time memory network model, realizing real-time prediction of earthquake damage, evaluating the damage grade of a structure according to an interlayer displacement limit value specified by a single building damage index, and finally realizing distribution prediction of multi-type structure frequent and rare earthquake damage in the area. The prediction method is reasonable, high in calculation efficiency and strong in popularization, and can be widely applied to intelligent evaluation of earthquake-resistant safety of urban building structure groups.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (8)

1. A building structure group seismic performance evaluation method is characterized by comprising the following steps:
acquiring an appearance picture of each monomer building in a target area, and respectively inputting the appearance picture into a structure type recognition model constructed based on a convolutional neural network for structure type recognition;
obtaining a remote sensing image of each single building and processing the remote sensing image to obtain the structural geometric dimension of each single building;
acquiring adjustable research information of each single building, and obtaining the internal hidden information of the structure of each single building based on a fuzzy reasoning method by combining the structure type of each single building;
building a building structure group simulation model based on the structure type, the structure geometric dimension and the structure internal hidden information of each single building;
determining a bedrock seismic power spectrum suitable for a target area according to the field category and the seismic intensity information, filtering a transfer function through a soil layer to obtain a surface seismic power spectrum, and further establishing a seismic dynamic field model of the target area;
building structure group earthquake dynamics models are built by combining the building structure group simulation models and the target area earthquake dynamic field models, earthquake response of each single building is calculated through earthquake response analysis, the earthquake response is input into a maximum interlayer displacement angle prediction model built based on a long-time memory network, the maximum interlayer displacement angle of each single building is obtained, and earthquake damage distribution of the building structure groups is evaluated by combining single building damage indexes.
2. The method for evaluating the seismic performance of the building structure group according to claim 1, wherein the structure type identification model is constructed on the basis of a Yolov5 neural network.
3. The method for evaluating earthquake-resistant performance of building structure groups according to claim 1, wherein the fuzzy inference method comprises:
taking the construction age as adjustable research information, and taking the material strength, construction measures and reinforcement conditions as hidden information inside the structure;
and establishing a double-input three-output fuzzy inference model with the construction age and the structure type as input and the material strength, the construction measures and the reinforcement condition as output for fuzzy inference.
4. The method according to claim 3, wherein the construction time domain is [ A, B ] in units of year, the fuzzy linguistic variables are "early" and "late", the membership function is bell-shaped, and year B is greater than year A; the structure type discourse domain is [1, 8], and the fuzzy linguistic variables are: the masonry structure, the frame structure, the shear wall structure, the frame-shear wall structure, the frame support structure, the cylinder structure, the frame cylinder structure and the large span structure are of eight types, and the membership function of the cylinder structure, the frame cylinder structure and the large span structure is triangular; the material strength discourse domain is [1, 5], and the fuzzy linguistic variables are: five types including low type, middle type, lower type, middle type and high type, and the membership function of the five types is a triangle; the construction measure domain is [0, 1], the fuzzy linguistic variable is 'present' and 'absent', and the membership function is a trapezoid; the reinforcement measure domain is [0, 1], the fuzzy linguistic variable is 'reinforcement not' and 'reinforcement', and the membership function is trapezoid.
5. The method for evaluating the seismic performance of the building structure group according to claim 1, wherein the target area seismic motion field model is established by a method comprising:
and generating a bedrock seismic power spectrum of the target area according to the field type and the seismic intensity information, taking the transfer effect of the seismic motion from bedrock to the earth surface into consideration, obtaining the earth surface power spectrum of each target point in the target area according to the soil layer filtering transfer function, and further generating the seismic motion time course corresponding to each target point.
6. The method for evaluating seismic performance of a group of building structures of claim 5, wherein the surface seismic power spectrum is:
S g (ω)＝|H n (ω)| 2 ×S n-1 (ω)＝|H n (ω)| 2 ×|H n-1 (ω)| 2 ×S n-2 (ω)＝…＝|H g (ω)| 2 ×S r (ω)
Figure FDA0003703115370000021
in the formula, ω represents a frequency; s g (ω) is the surface seismic power spectrum; s r (ω) is the seismic power spectrum with the bedrock; h i (ω) is the soil layer filtration transfer function for each layer of soil, expressed as:
Figure FDA0003703115370000022
in the formula, xi i Represents the energy transfer dissipation damping ratio, gamma, of the i-th layer of soil i Is the reflection coefficient, tau, at the layer boundary of the i-th layer soil i The propagation time of the seismic waves in the ith layer of soil is obtained; gamma ray i And τ i Respectively expressed as:
Figure FDA0003703115370000023
τ i ＝h i /υ i
in the formula, ρ i Denotes the density, upsilon, of the i-th layer of soil i Representing the propagation wave velocity h of seismic waves in the i-th layer of soil i The thickness of the ith soil layer is shown.
7. The method for evaluating the earthquake resistance of the building structure group according to claim 1, wherein the maximum interlayer displacement angle prediction model is constructed based on a long-and-short time memory network model, the earthquake response is used as input, the maximum interlayer displacement angle is used as output, and a particle swarm algorithm is adopted to optimize model parameters in the training process.
8. The method for evaluating earthquake damage resistance of building structure group according to claim 1, wherein the evaluation of earthquake damage distribution of building structure group in combination with individual building damage index comprises:
simulating the situation that earthquakes with different intensities occur in a target area based on the building structure group earthquake dynamics model to obtain the maximum interlayer displacement angle of each monomer building under different earthquake intensities;
comparing the maximum interlayer displacement angle of each monomer building with an interlayer displacement limit value specified by a monomer building damage index, and grading each monomer building to be one of intact, basically intact, slightly damaged, moderately damaged, severely damaged and collapsed;
and calibrating each single building according to grades to obtain the earthquake damage distribution of building structure groups in different earthquake intensities of the target area.
CN202210697162.XA 2022-06-20 2022-06-20 Building structure group earthquake-resistant performance evaluation method Pending CN115017591A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210697162.XA CN115017591A (en) 2022-06-20 2022-06-20 Building structure group earthquake-resistant performance evaluation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210697162.XA CN115017591A (en) 2022-06-20 2022-06-20 Building structure group earthquake-resistant performance evaluation method

Publications (1)

Publication Number Publication Date
CN115017591A true CN115017591A (en) 2022-09-06

Family

ID=83075071

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210697162.XA Pending CN115017591A (en) 2022-06-20 2022-06-20 Building structure group earthquake-resistant performance evaluation method

Country Status (1)

Country Link
CN (1) CN115017591A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115660759A (en) * 2022-12-29 2023-01-31 成都阿卡林科技发展有限公司 Real estate value prediction system and method based on big data analysis
CN116310791A (en) * 2023-01-19 2023-06-23 中国地震台网中心 Rapid judgment method and electronic equipment for extremely disaster area based on building earthquake damage detection
CN116821642A (en) * 2023-06-13 2023-09-29 北京建筑大学 Building earthquake damage rapid assessment method and system based on data augmentation and deep learning
CN117077439A (en) * 2023-10-13 2023-11-17 中国建筑科学研究院有限公司 Technical method, device and storage medium for checking hidden danger of building earthquake resistance
CN117494590A (en) * 2024-01-03 2024-02-02 国泰新点软件股份有限公司 Method, device, equipment and storage medium for evaluating earthquake resistance of building facilities
CN117972437A (en) * 2024-03-29 2024-05-03 四川省建筑设计研究院有限公司 Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115660759A (en) * 2022-12-29 2023-01-31 成都阿卡林科技发展有限公司 Real estate value prediction system and method based on big data analysis
CN116310791A (en) * 2023-01-19 2023-06-23 中国地震台网中心 Rapid judgment method and electronic equipment for extremely disaster area based on building earthquake damage detection
CN116310791B (en) * 2023-01-19 2023-09-05 中国地震台网中心 Rapid judgment method and electronic equipment for extremely disaster area based on building earthquake damage detection
CN116821642A (en) * 2023-06-13 2023-09-29 北京建筑大学 Building earthquake damage rapid assessment method and system based on data augmentation and deep learning
CN117077439A (en) * 2023-10-13 2023-11-17 中国建筑科学研究院有限公司 Technical method, device and storage medium for checking hidden danger of building earthquake resistance
CN117077439B (en) * 2023-10-13 2024-02-23 中国建筑科学研究院有限公司 Technical method, device and storage medium for checking hidden danger of building earthquake resistance
CN117494590A (en) * 2024-01-03 2024-02-02 国泰新点软件股份有限公司 Method, device, equipment and storage medium for evaluating earthquake resistance of building facilities
CN117494590B (en) * 2024-01-03 2024-04-05 国泰新点软件股份有限公司 Method, device, equipment and storage medium for evaluating earthquake resistance of building facilities
CN117972437A (en) * 2024-03-29 2024-05-03 四川省建筑设计研究院有限公司 Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions

Similar Documents

Publication Publication Date Title
CN115017591A (en) Building structure group earthquake-resistant performance evaluation method
WO2022242435A1 (en) Rapid evaluation method of site seismic liquefaction disaster based on artificial intelligence
KR100982447B1 (en) Landslide occurrence prediction system and predicting method using the same
CN113779835A (en) AI and intelligent monitoring system based deep and large foundation pit safety early warning method
CN114971301B (en) Ecological interference risk identification and evaluation method based on automatic parameter adjustment optimization model
CN109886456B (en) Debris flow prediction method based on PCA and mixed kernel function LSSVR
CN113554849A (en) Air-ground monitoring slope system and instability risk assessment method thereof
CN113610301B (en) Prediction algorithm for representing ground settlement time sequence evolution
CN111027881B (en) Transmission tower natural disaster loss evaluation method based on improved grey correlation degree
CN113033997A (en) Urban water quality grade determination method, device and medium based on improved set pair analysis
CN108229726A (en) A kind of shiver stone side slope catastrophe dangerous situation early alarming and forecasting method
CN110956412A (en) Flood dynamic assessment method, device, medium and equipment based on real-scene model
CN115629160A (en) Air pollutant concentration prediction method and system based on space-time diagram
CN112035941A (en) Prediction method for surface subsidence of deep foundation pit excavation based on BAS-BP model
Dogan et al. Detection of damages caused by earthquake and reinforcement corrosion in RC buildings with Deep Transfer Learning
Keke et al. STGA-CBR: a case-based reasoning method based on spatiotemporal trajectory similarity assessment
CN115829150A (en) Accumulated water prediction system
CN111767649B (en) Soft foundation area transformer substation geological deformation safety assessment method
CN115438547A (en) Overall evaluation method and system based on pavement service state
CN114548585A (en) Urban building earthquake damage prediction method based on neural network
CN112862144A (en) Method for determining optimal loss curve of non-material city based on double-layer target optimization
CN110674471A (en) Debris flow easiness prediction method based on GIS (geographic information System) and Logistic regression model
CN115936309B (en) Building health monitoring method and system based on multi-feature factor integrated evaluation
CN111753470B (en) Building energy consumption prediction method based on rough set and deep belief neural network
CN116310791B (en) Rapid judgment method and electronic equipment for extremely disaster area based on building earthquake damage detection

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