Urban anti-seismic toughness evaluation method and system

Abstract

The invention discloses a city anti-seismic toughness evaluation method and system, and relates to the technical field of building intelligent evaluation. The method comprises the following specific steps: determining a criterion layer and an index layer of urban shock resistance toughness evaluation; performing data preprocessing on the index layer to obtain screened evaluation indexes; calculating the screened evaluation indexes by adopting a combination weighting method to obtain an optimal combination weight; according to the optimal combination weight, the evaluation index is weighted, and a city shock resistance toughness index system is established; and obtaining a pre-constructed urban anti-seismic performance evaluation model, inputting the urban anti-seismic toughness index system into the urban anti-seismic performance evaluation model, and outputting a toughness evaluation result. According to the method, the machine learning technology is applied to the field of urban anti-seismic toughness evaluation, semantic understanding and analysis are performed by using a data processing and analysis algorithm based on a deep learning neural network, the urban anti-seismic toughness is evaluated, and the evaluation efficiency and the reliability of an evaluation result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent building assessment, and in particular to a method and system for assessing urban seismic resilience. Background Art

[0002] With the development of social economy, cities have become economic and population gathering places. Once an earthquake occurs, it will bring huge economic losses and casualties to the city. Nowadays, the two concepts of "resilience" and "resilient city" are often used to define the city's disaster prevention and mitigation capabilities. "Resilience" is considered to be an important expression or core of sustainability. It is a series of comprehensive states such as changes and transitions when a system faces disturbances. A city that has the ability to resist disasters or recover after being damaged by disasters can be called a "resilient city." In the existing technology, it mainly relies on empirical evaluation methods to evaluate the seismic performance of cities. The empirical evaluation method is usually performed by evaluators based on professional experience to evaluate the seismic performance of buildings. It takes a lot of manpower and time to collect and process data on housing buildings and municipal facilities, and then calculates based on statistical analysis and empirical formulas. The data processing efficiency is low and the calculation accuracy of the seismic hazard evaluation index is not high. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for evaluating urban seismic resilience, so as to solve the problems raised in the background technology and realize accurate and efficient evaluation of urban seismic resilience.

[0004] To achieve the above object, the present invention provides the following solutions: On the one hand, a method for evaluating urban seismic resilience is provided, and the specific steps include the following:

[0005] Establish the criteria and indicator layers for evaluating urban seismic resilience;

[0006] Performing data preprocessing on the indicator layer to obtain screened evaluation indicators;

[0007] The combined weighting method is used to calculate the optimal combined weights of the selected evaluation indicators;

[0008] Assign weights to the evaluation indicators according to the optimal combination weights, and establish an urban seismic resilience index system;

[0009] A pre-constructed urban seismic performance assessment model is obtained, the urban seismic resilience index system is input into the urban seismic performance assessment model, and a resilience assessment result is output.

[0010] Preferably, the step of calculating the optimal combination weight using the combination weighting method is:

[0011] The improved AHP method is used to determine the quantified subjective weight of each evaluation index in the index layer;

[0012] The entropy weight method is used to determine the objective weight of each evaluation indicator in the indicator layer;

[0013] The subjective weight and the objective weight are fused and calculated to obtain the optimal combined weight.

[0014] Preferably, the urban seismic performance assessment model is a convolutional neural network model that takes the urban seismic resilience index system as input and takes the resilience assessment results as output.

[0015] Preferably, the training process of the urban seismic performance assessment model is:

[0016] Get the neural network structure parameters;

[0017] According to the neural network structure parameters, a target search structure set is constructed, and a training set is input into the neural network to obtain an output result;

[0018] Acquire multiple evaluation indicators of the neural network structure, wherein the evaluation indicators include any multiple of the accuracy, parameter quantity and running time of the neural network structure;

[0019] Based on the multiple evaluation indicators and the target search structure set, the neural network is iteratively trained until the loss value of the loss function meets the target convergence condition, and the training is stopped to obtain the urban seismic performance evaluation model.

[0020] Preferably, the criterion layer includes urban facility resilience, economic resilience, emergency management system resilience, social resilience, and ecological environmental resilience.

[0021] Preferably, the step of performing data preprocessing on the indicator layer is:

[0022] The KMO method is used to calculate the KMO value of each indicator in the indicator layer;

[0023] If the calculated KMO value is greater than the set redundancy threshold, the indicator will be eliminated.

[0024] Preferably, the method further includes grading the toughness assessment results, issuing warning information of corresponding levels according to the grading results, and taking emergency measures according to the warning information.

[0025] On the other hand, a system for evaluating urban seismic resilience is provided, including an index determination module, a preprocessing module, a weight calculation module, an index system establishment module, and an evaluation module; wherein:

[0026] The indicator determination module is used to establish the criterion layer and indicator layer of urban seismic resilience evaluation;

[0027] The preprocessing module is used to perform data preprocessing on the indicator layer to obtain the screened evaluation indicators;

[0028] The weight calculation module is used to calculate the optimal combined weight by using the combined weighting method for the selected evaluation indicators;

[0029] The indicator system establishment module is used to weight the evaluation indicators according to the optimal combination weights to establish an urban seismic resilience indicator system;

[0030] The evaluation module is used to obtain a pre-constructed urban seismic performance evaluation model, input the urban seismic resilience index system into the urban seismic performance evaluation model, and output a resilience evaluation result.

[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] (1) Apply machine learning technology to the field of urban seismic resilience assessment, and use data processing and analysis algorithms based on deep learning neural networks to perform semantic understanding and analysis to assess the seismic resilience of cities, thereby improving the evaluation efficiency and reliability of the evaluation results. The system can automatically process and analyze the urban seismic resistance situation and provide decision makers with data-based evaluation results;

[0033] (2) It improves the accuracy of seismic resilience evaluation and provides a reference for the seismic resilience evaluation of various urban elements;

[0034] (3) In the present invention, a low-redundancy urban seismic resilience evaluation index system is constructed, which greatly improves the rationality and scientificity of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 is a flow chart of the method of the present invention;

[0037] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The purpose of this invention is to provide a method for evaluating urban seismic resilience. Figure 1 As shown, the specific steps include the following:

[0040] S1. Establish the criteria and indicator layers for evaluating urban seismic resilience;

[0041] S2, preprocess the data of the indicator layer to obtain the selected evaluation indicators;

[0042] S3, using the combined weighting method to calculate the optimal combined weights for the selected evaluation indicators;

[0043] S4. Weight the evaluation indicators according to the optimal combination weights to establish an urban seismic resilience index system;

[0044] S5. Obtain a pre-constructed urban seismic performance assessment model, input the urban seismic resilience index system into the urban seismic performance assessment model, and output the resilience assessment result.

[0045] Furthermore, in step S1, the criteria layer for evaluating urban resilience is established through expert interviews and relevant literature mining and analysis, including urban facility resilience, economic resilience, emergency management system resilience, social resilience, and ecological environmental resilience. Each dimension in the criteria layer corresponds to multiple indicators in the indicator layer.

[0046] The principles for selecting urban resilience evaluation indicators are as follows:

[0047] 1. Feasibility

[0048] In the process of selecting evaluation indicators, the actual situation of obtaining relevant information, data and quantitative methods should be considered. The selected indicators should be practical and easy to implement to reduce the difficulty of the statistical and analytical process.

[0049] 2. Scientificity

[0050] In the process of establishing the indicator system, the principles of establishing the indicator system are strictly adhered to, and scientific methods are used in the selection of indicators, the construction of the indicator system, the calculation of indicator weights and the evaluation of urban resilience.

[0051] 3. Necessity

[0052] Necessity means that each indicator is necessary and cannot be replaced by other indicators. The selected indicators can scientifically, truly and independently reflect the various characteristics of urban seismic resilience. The necessity principle of indicator selection can effectively improve the evaluation efficiency of the indicator system, accurately select the required indicators, and more accurately evaluate the urban seismic resilience.

[0053] Urban facilities refer to various facilities in the city that maintain their normal operation, including public facilities and non-public facilities. In earthquake-prone areas, the seismic design and construction quality of buildings are the most critical factors for cities to cope with earthquakes. In this embodiment, the indicators corresponding to the resilience of urban facilities are: the proportion of reinforced concrete houses, per capita refuge area, and road network density.

[0054] Furthermore, economic resilience mainly refers to the ability of the regional economy to cope with risks, which includes three aspects: the economic resilience of the government, the economic resilience of residents and the economic resilience of society as a whole. Therefore, the corresponding indicators of economic resilience are: GDP, unemployment rate, and per capita income level.

[0055] Furthermore, earthquakes are vibrations caused by the collision of the earth's plates. On average, tens of thousands of earthquakes occur every day, of which more than ten or dozens of earthquakes will cause harm to humans. At present, humans cannot predict earthquakes, but can only do a good job of earthquake defense and minimize earthquake losses. The emergency management system makes emergency preparations and responses to prevent and control potential accidents or emergencies. The indicators corresponding to the resilience of the emergency management system are: the number of community comprehensive disaster reduction regulations, the number of emergency rescue tents per 10,000 people, and the number of emergency knowledge manuals issued.

[0056] Furthermore, social resilience refers to the resilience of society as a whole and individuals. Social resilience as a whole refers to the ability of the entire society to resist natural disasters such as earthquakes, while social individual resilience refers to the attributes of people in society. The indicators corresponding to social resilience are: population density, aging level, and medical insurance participation rate.

[0057] Furthermore, the ecological environment refers to the quantity and quality of water, land, biological resources, and climate resources that affect human survival and development. It is a complex ecosystem related to the sustainable development of society and economy. The indicators corresponding to the resilience of the ecological environment are: forest coverage, number of extreme weather warnings, and age of buildings.

[0058] Furthermore, in order to avoid the redundancy of the selected indicators, the KMO method is used to test their redundancy. The steps of data preprocessing on the indicator layer in step S2 are:

[0059] S21. Calculate the KMO value of each indicator in the indicator layer using the KMO method;

[0060] S22. If the calculated KMO value is greater than the set redundancy threshold, the indicator is eliminated.

[0061] Furthermore, in step S3, the steps of using the combined weighting method to calculate the optimal combined weight are:

[0062] S31. Use the improved AHP method to determine the quantified subjective weight of each evaluation indicator in the indicator layer;

[0063] S32. Use the entropy weight method to determine the objective weight of each evaluation indicator in the indicator layer;

[0064] S33, the subjective weight and the objective weight are integrated and calculated to obtain the optimal combined weight.

[0065] Furthermore, the urban seismic performance assessment model is a convolutional neural network model that takes the urban seismic resilience index system as input and the resilience assessment results as output.

[0066] The training process of the urban seismic performance assessment model is as follows:

[0067] S51, obtaining neural network structure parameters;

[0068] S52, constructing a target search structure set according to the neural network structure parameters, inputting the training set into the neural network, and obtaining an output result;

[0069] S53, obtaining multiple evaluation indicators of the neural network structure, where the evaluation indicators include any multiple of the accuracy, parameter quantity and running time of the neural network structure;

[0070] S54, based on multiple evaluation indicators and the target search structure set, iteratively train the neural network until the loss value of the loss function meets the target convergence condition, stop the training, and obtain the urban seismic performance evaluation model.

[0071] Furthermore, it also includes grading the resilience assessment results, issuing warning information of corresponding levels according to the grading results, and taking emergency measures based on the warning information.

[0072] Another embodiment of the present invention provides a system for evaluating urban seismic resilience. Figure 2 As shown, it includes an indicator determination module, a preprocessing module, a weight calculation module, an indicator system establishment module, and an evaluation module; among which,

[0073] The indicator determination module is used to establish the criterion layer and indicator layer for urban seismic resilience evaluation;

[0074] The preprocessing module is used to preprocess the data of the indicator layer and obtain the screened evaluation indicators;

[0075] The weight calculation module is used to calculate the optimal combination weight using the combined weighting method for the selected evaluation indicators;

[0076] An indicator system establishment module is used to weight the evaluation indicators according to the optimal combination weights to establish an urban seismic resilience indicator system;

[0077] The evaluation module is used to obtain a pre-built urban seismic performance evaluation model, input the urban seismic resilience index system into the urban seismic performance evaluation model, and output the resilience evaluation result.

[0078] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating urban seismic resilience, characterized in that: The specific steps include the following: Establish the criteria and indicator layers for evaluating urban seismic resilience; Performing data preprocessing on the indicator layer to obtain screened evaluation indicators; The combined weighting method is used to calculate the optimal combined weights of the selected evaluation indicators; Assign weights to the evaluation indicators according to the optimal combination weights, and establish an urban seismic resilience index system; A pre-constructed urban seismic performance assessment model is obtained, the urban seismic resilience index system is input into the urban seismic performance assessment model, and a resilience assessment result is output.

2. A method for evaluating urban seismic resilience according to claim 1, characterized in that: The steps of using the combined weighting method to calculate the optimal combined weight are: The improved AHP method is used to determine the quantified subjective weight of each evaluation index in the index layer; The entropy weight method is used to determine the objective weight of each evaluation indicator in the indicator layer; The subjective weight and the objective weight are fused and calculated to obtain the optimal combined weight.

3. A method for evaluating urban seismic resilience according to claim 1, characterized in that: The urban seismic performance assessment model is a convolutional neural network model that takes the urban seismic resilience index system as input and takes the resilience assessment results as output.

4. A method for evaluating urban seismic resilience according to claim 1, characterized in that: The training process of the urban seismic performance assessment model is as follows: Get the neural network structure parameters; According to the neural network structure parameters, a target search structure set is constructed, and a training set is input into the neural network to obtain an output result; Acquire multiple evaluation indicators of the neural network structure, wherein the evaluation indicators include any multiple of the accuracy, parameter quantity and running time of the neural network structure; Based on the multiple evaluation indicators and the target search structure set, the neural network is iteratively trained until the loss value of the loss function meets the target convergence condition, and the training is stopped to obtain the urban seismic performance evaluation model.

5. The urban seismic resilience evaluation method according to claim 1 is characterized in that: The criteria layers include urban facility resilience, economic resilience, emergency management system resilience, social resilience, and ecological environmental resilience.

6. A method for evaluating urban seismic resilience according to claim 1, characterized in that: The steps of performing data preprocessing on the indicator layer are: The KMO method is used to calculate the KMO value of each indicator in the indicator layer; If the calculated KMO value is greater than the set redundancy threshold, the indicator will be eliminated.

7. The urban seismic resilience evaluation method according to claim 1 is characterized in that: It also includes grading the resilience assessment results, issuing warning information of corresponding levels according to the grading results, and taking emergency measures according to the warning information.

8. A system for evaluating urban seismic resilience, characterized in that: It includes indicator determination module, preprocessing module, weight calculation module, indicator system establishment module and evaluation module; among them, The indicator determination module is used to establish the criterion layer and indicator layer of urban seismic resilience evaluation; The preprocessing module is used to perform data preprocessing on the indicator layer to obtain the screened evaluation indicators; The weight calculation module is used to calculate the optimal combined weight by using the combined weighting method for the selected evaluation indicators; The indicator system establishment module is used to weight the evaluation indicators according to the optimal combination weights to establish an urban seismic resilience indicator system; The evaluation module is used to obtain a pre-constructed urban seismic performance evaluation model, input the urban seismic resilience index system into the urban seismic performance evaluation model, and output a resilience evaluation result.

Images