Building deformation risk identification method, device, equipment, medium and product

Abstract

This application discloses a method, device, equipment, medium, and product for identifying building deformation risks, belonging to the field of building deformation risk assessment technology. The method includes: constructing a multi-level index system for building deformation risk assessment in ground settlement areas; taking building deformation risk level assessment as the target layer; selecting ground settlement susceptibility, building structural attributes, InSAR deformation monitoring, and external construction disturbance as the criterion layers; and refining the criterion layers by setting index layers; performing membership quantification on each index in the index layers to obtain the membership degree vector of each index; constructing the weights of each level of indexes based on the analytic hierarchy process (AHP); constructing a fuzzy evaluation matrix based on the membership degree vectors; and obtaining the comprehensive risk membership degree vector of the target layer based on the fuzzy weighted average method according to the criterion layer weight vectors and the index layer weight vectors; and determining the final deformation risk level of the building based on the principle of maximum membership degree. The embodiments of this application can improve the accuracy of identifying building deformation risks.

Description

Technical Field

[0001] This application relates to the field of building deformation risk assessment technology, and in particular to a method, device, equipment, medium and product for identifying building deformation risks. Background Technology

[0002] In the process of urbanization, groundwater extraction, engineering construction and other activities can easily cause ground subsidence. Urban ground subsidence can further cause uneven settlement of buildings, wall cracking, structural deformation and other problems. In severe cases, it can even lead to building collapse. Therefore, there is an urgent need for scientific building deformation risk assessment methods.

[0003] Currently, existing technologies mostly rely on interferometric synthetic aperture radar (InSAR) for assessment. However, the evaluation indicators are singular and lack comprehensive consideration of factors such as building structure, geological background, and construction disturbance. Furthermore, the assessment models are mainly qualitative / semi-quantitative methods, which are highly subjective or dependent on data, making it difficult to handle fuzzy indicators. This results in insufficient alignment between the assessment results and the actual engineering situation, making it difficult to accurately identify the building deformation risk in areas of ground subsidence. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium, and product for identifying building deformation risks, which can effectively improve the accuracy of identifying building deformation risks.

[0005] To achieve the above objectives, a first aspect of this application provides a method for identifying building deformation risks, comprising: A multi-level index system for assessing building deformation risk in areas of ground settlement is constructed. The building deformation risk level assessment is taken as the target layer, and ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance are selected as the criteria layers. An index layer is set to refine each of the criteria layers. The membership degree vector of each indicator in the indicator layer is obtained by performing membership degree quantification on each indicator to the preset risk level. The weights of indicators at each level are constructed based on the analytic hierarchy process, resulting in the weight vectors of the criteria layer and the indicator layer. A fuzzy evaluation matrix is ​​constructed based on the membership vector, and a multi-level fuzzy comprehensive evaluation is performed based on the fuzzy weighted average method according to the criterion layer weight vector and the index layer weight vector to obtain the comprehensive risk membership vector of the target layer. Based on the principle of maximum membership, the final deformation risk level of the building is determined from the comprehensive risk membership vector of the target layer.

[0006] Compared with existing technologies, the building deformation risk identification method provided in this application has the following advantages: It constructs a multi-level indicator system with ground settlement susceptibility, building structural attributes, InSAR deformation monitoring, and external construction disturbance as the criterion layer, achieving comprehensive coverage of factors influencing building deformation risk and solving the problem of single traditional assessment indicators; by performing membership quantification processing on the indicators at the indicator layer, fuzzy assessment information is transformed into calculable quantitative data, achieving a unified quantitative expression for different types of indicators; based on the analytic hierarchy process, the weights of each level of indicators are scientifically constructed, clarifying the degree of influence of different indicators on the deformation risk assessment results and quantifying the relative importance among indicators; by combining weight vectors and membership vectors to conduct multi-level fuzzy comprehensive evaluation, the organic integration and comprehensive calculation of assessment data from various dimensions and indicators are achieved, improving the scientificity and objectivity of the assessment results; finally, based on the principle of maximum membership, the building deformation risk level is directly determined, simplifying the assessment result determination process, ensuring the accuracy of the determination results, and effectively improving the comprehensiveness, accuracy, and efficiency of building deformation risk identification in ground settlement areas.

[0007] In some embodiments, the step of performing membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to a preset risk level includes: For the quantitative indicators in the indicator layer, the quantitative indicators include deformation rate, cumulative deformation and tilt rate. First, risk level classification thresholds are set for the deformation rate, cumulative deformation and tilt rate respectively. Then, a piecewise membership function is used to map the measured values ​​of the quantitative indicators to the membership degree of each risk level in the corresponding preset risk level. After obtaining the initial membership vector, normalization processing is performed to obtain the membership vector of each quantitative indicator to the preset risk level. For the qualitative indicators in the indicator layer, a membership vector corresponding to a preset risk level is assigned to each qualitative indicator according to the preset qualitative indicator risk membership assignment table.

[0008] In some embodiments, the construction of indicator weights at each level based on the analytic hierarchy process (AHP) to obtain the criterion-level weight vector and the indicator-level weight vector includes: Construct initial fuzzy judgment matrices for each level of the criterion layer relative to the target layer and for each level of the indicator layer relative to the corresponding criterion layer; Each of the initial fuzzy judgment matrices is transformed into a fuzzy consistency matrix; The fuzzy consistency matrices are summed row by row, and after normalization, the weight vectors of each level are obtained, which are then used to obtain the weight vectors of the criterion layer and the weight vectors of each index layer. The consistency of each fuzzy consistency matrix is ​​checked using a fuzzy consistency ratio. If the fuzzy consistency ratio is less than a preset threshold, the matrix is ​​determined to meet the consistency requirements.

[0009] In some embodiments, the step of constructing a fuzzy evaluation matrix based on the membership vector, and performing a multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the criterion layer weight vector and the index layer weight vector to obtain the comprehensive risk membership vector of the target layer includes: Based on the membership vectors of each indicator in the indicator layer, construct the fuzzy evaluation matrix corresponding to each criterion layer. The weight vectors of each indicator layer are combined with the fuzzy evaluation matrix of the corresponding criterion layer to obtain the comprehensive risk membership vector of each criterion layer. By combining the comprehensive risk membership vectors of all criterion layers, a fuzzy evaluation matrix for the target layer is constructed. The fuzzy synthesis operation is performed between the criterion layer weight vector and the target layer fuzzy evaluation matrix to obtain the comprehensive risk membership vector of the target layer.

[0010] In some embodiments, the index layer for ground subsidence susceptibility includes high susceptibility, medium susceptibility, and low susceptibility; The index layer of building structural attributes includes reinforced concrete, mixed structure, brick-wood structure, and simple structure; The InSAR deformation monitoring index layer includes deformation rate, cumulative deformation, and tilt rate; The index layer for external construction disturbance includes yes and no.

[0011] In some embodiments, determining the final deformation risk level of a building from the comprehensive risk membership vector of the target layer based on the maximum membership principle includes: The risk level corresponding to the maximum value in the target layer's comprehensive risk membership vector is determined as the final deformation risk level of buildings in the ground subsidence area.

[0012] To achieve the above objectives, a second aspect of this application provides a building deformation risk identification device, the device comprising: The module is used to construct a multi-level index system for assessing building deformation risk in areas of ground settlement. The target layer is the assessment of building deformation risk level. The criteria layers are ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance. The index layers are set to refine each of the criteria layers. The quantification module is used to perform membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to the preset risk level. The analysis module is used to construct the weights of indicators at each level based on the analytic hierarchy process (AHP) to obtain the weight vectors of the criteria layer and the indicator layer. The weighting module is used to construct a fuzzy evaluation matrix based on the membership vector, and to perform multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the criterion layer weight vector and the index layer weight vector to obtain the comprehensive risk membership vector of the target layer. The determination module is used to determine the final deformation risk level of the building from the comprehensive risk membership vector of the target layer based on the principle of maximum membership.

[0013] To achieve the above objectives, a third aspect of this application provides an electronic device, the electronic device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described in the first aspect.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed, controls the device containing the computer-readable storage medium to perform the method described in the first aspect.

[0015] To achieve the above objectives, a fifth aspect of the present application provides a computer program product, which includes a computer program or computer instructions, wherein the computer program or computer instructions, when executed by a processor, implement the method described in the first aspect. Attached Figure Description

[0016] Figure 1 This is a flowchart of a building deformation risk identification method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the function of each risk membership degree of the deformation rate provided in the embodiments of this application; Figure 3 This is a schematic diagram of a building deformation risk identification device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0021] First, let's analyze some of the terms used in this application: Membership degree: In fuzzy mathematics, it is a quantitative index that represents the degree to which an element belongs to a certain fuzzy set. The value range is [0,1]. The larger the value, the higher the degree to which the element belongs to the fuzzy set. 0 means no membership at all, and 1 means full membership in the set. It is the basis for realizing the quantitative description and analysis of fuzzy index.

[0022] In the process of urbanization, groundwater extraction, engineering construction and other activities can easily cause ground subsidence. Urban ground subsidence can further cause uneven settlement of buildings, wall cracking, structural deformation and other problems. In severe cases, it can even lead to building collapse. Therefore, there is an urgent need for scientific building deformation risk assessment methods.

[0023] Currently, related technologies such as Synthetic Aperture Radar Interferometry (InSAR) have been successfully applied to the monitoring of land subsidence and building deformation due to their advantages of all-weather operation, wide coverage, cloud and fog-free operation, and high-precision measurement. However, in terms of evaluation index systems, existing studies mostly focus on quantitative monitoring indicators such as deformation rate, cumulative deformation, and tilt rate interpreted by InSAR, lacking integration of inherent attribute elements such as building structure type. Furthermore, there is a significant lack of consideration for external disturbance factors such as foundation pit construction and external loads. The comprehensiveness and engineering adaptability of the index system need to be improved.

[0024] At the risk assessment model level, data-driven models such as machine learning are difficult to implement effectively due to limitations such as the limited number of assessment samples and the difficulty in acquiring data. Existing assessment methods are mainly qualitative / semi-quantitative: among them, expert scoring and safety checklist methods are easy to operate, but they suffer from strong subjectivity and difficulty in quantifying indicator weights; numerical simulation methods, while having high assessment accuracy, have strict requirements for data completeness, are difficult to effectively handle fuzzy information in the indicator system, and have high engineering application costs and insufficient scalability.

[0025] Based on this, embodiments of this application provide a method, apparatus, equipment, medium, and product for identifying building deformation risks, which can effectively improve the accuracy of identifying building deformation risks.

[0026] Please see Figure 1 , Figure 1 This is an optional flowchart of the building deformation risk identification method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0027] Step S101: Construct a multi-level index system for risk assessment of building deformation in ground settlement areas. With the building deformation risk level assessment as the target layer, select ground settlement susceptibility, building structural attributes, InSAR deformation monitoring, and external construction disturbance as the criteria layers, and set index layers to refine each criteria layer. Step S102: Perform membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to the preset risk level. Step S103: Construct the weights of each level of indicators based on the analytic hierarchy process (AHP) to obtain the weight vectors of the criterion layer and the weight vectors of the indicator layer. Step S104: Construct a fuzzy evaluation matrix based on the membership vector, and perform multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the criterion layer weight vector and the indicator layer weight vector to obtain the comprehensive risk membership vector of the target layer. Step S105: Based on the principle of maximum membership, determine the final deformation risk level of the building from the comprehensive risk membership vector of the target layer.

[0028] Steps S101 to S105 of this embodiment, by constructing a multi-level indicator system with ground settlement susceptibility, building structural attributes, InSAR deformation monitoring, and external construction disturbance as the criterion layer, achieve comprehensive coverage of factors influencing building deformation risk and solve the problem of single traditional assessment indicators. By performing membership quantification on the indicators at the indicator layer, fuzzy assessment information is transformed into calculable quantitative data, realizing a unified quantitative expression for different types of indicators. Based on the analytic hierarchy process, the weights of each level of indicators are scientifically constructed, clarifying the degree of influence of different indicators on the deformation risk assessment results and quantifying the relative importance among indicators. By combining weight vectors and membership vectors to carry out multi-level fuzzy comprehensive evaluation, the organic integration and comprehensive calculation of assessment data of various dimensions and indicators are realized, improving the scientificity and objectivity of the assessment results. Finally, the building deformation risk level is directly determined based on the principle of maximum membership, simplifying the assessment result determination process, ensuring the accuracy of the determination results, and effectively improving the comprehensiveness, accuracy, and efficiency of building deformation risk identification in ground settlement areas.

[0029] In step S101 of some embodiments, the multi-level indicator system can be a three-level evaluation indicator system divided into a target layer, a criterion layer, and an indicator layer. The target layer can be the building deformation risk level assessment. The criterion layer can be the key dimensions affecting the assessment results of the target layer. In this embodiment, four dimensions are specifically selected: ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance. The indicator layer is a further refinement and breakdown of each dimension of the criterion layer. It is a basic indicator that can be directly used for quantitative / qualitative evaluation, providing specific judgment basis for the criterion layer assessment.

[0030] In some embodiments, the index layer for ground settlement susceptibility includes high susceptibility, medium susceptibility, and low susceptibility; the index layer for building structural properties includes reinforced concrete, mixed structure, brick-wood structure, and simple structure; the index layer for InSAR deformation monitoring includes deformation rate, cumulative deformation, and tilt rate; and the index layer for external construction disturbance includes yes and no.

[0031] Specifically, the target layer (A) is the assessment of the deformation risk level of buildings in the ground settlement area; the four major dimensions that have the main influence on the deformation risk of buildings in the ground settlement area are selected as the criterion layer (B), specifically including ground settlement susceptibility (B1), building structural properties (B2), InSAR deformation monitoring (B3), and external construction disturbance (B4); each criterion layer is further refined into an indicator layer (C) according to the actual assessment needs, and risk levels are preset to form an evaluation set V={very low risk, low risk, medium risk, high risk}. The specific multi-level indicator system can be represented by Table 1 below: Table 1. Multi-level index system for building deformation risk assessment in ground settlement areas

[0032] In step S102 of some embodiments, membership degree is a quantitative indicator in fuzzy mathematics that represents the degree to which an element belongs to a certain fuzzy set. Its value range is [0,1], where 0 represents no membership at all and 1 represents full membership in the set. In this embodiment, membership degree can specifically be the degree value of each indicator in the indicator layer belonging to a certain deformation risk level. The preset risk level can be a pre-defined building deformation risk classification standard; in this embodiment, it is a four-level risk level: extremely low risk, low risk, medium risk, and high risk. The membership degree vector can be a vector composed of the membership degree values ​​of each indicator to the preset risk level in sequence, with the dimension consistent with the number of preset risk levels.

[0033] In some embodiments, the membership metric of each indicator in the indicator layer is quantified to obtain the membership vector of each indicator to a preset risk level, including: For the quantitative indicators in the indicator layer, which include deformation rate, cumulative deformation and tilt rate, risk level classification thresholds are first set for deformation rate, cumulative deformation and tilt rate respectively. Then, a piecewise membership function is used to map the measured values ​​of the quantitative indicators to the membership degree of each risk level in the corresponding preset risk level. After obtaining the initial membership vector, normalization is performed to obtain the membership vector of each quantitative indicator to the preset risk level. For qualitative indicators in the indicator layer, a membership vector corresponding to a preset risk level is assigned to each qualitative indicator according to the preset qualitative indicator risk membership assignment table.

[0034] Specifically, for the different attributes of qualitative and quantitative indicators in the indicator layer, the membership degree of each indicator to the preset risk level is determined by using fixed membership degree assignment and membership degree function calculation methods respectively.

[0035] For the quantitative indicators in the indicator layer, risk level classification thresholds are first set for deformation rate, cumulative deformation, and tilt rate. The thresholds can be determined by combining the "Code for Measurement of Building Deformation" (JGJ 8-2016), the "Code for Design of Building Foundations" (GB 50007-2011), and engineering practices in ground settlement areas. The four-level classification thresholds (extremely low risk, low risk, medium risk, and high risk) corresponding to each quantitative indicator are clearly defined. The thresholds for each indicator must cover the common range of actual monitoring data. Then, a piecewise membership function is used to map the measured values ​​of the quantitative indicators to the membership degrees corresponding to each risk level, obtaining the initial membership vector.

[0036] The membership function employs a combination of semi-trapezoidal and triangular distributions. The measured values ​​of the set quantity index are... The risk level classification thresholds for extremely low risk, low risk, medium risk, and high risk are as follows: , , , These correspond to membership functions with extremely low risk. Low-risk membership function Membership function of medium risk High-risk membership functions Specifically, it can be expressed by the following formula:

[0037] Taking deformation rate as an example, =0.1, =1, =3, =10, the membership function distribution of each level of risk is as follows Figure 2 As shown in Table 2 below, the risk level classification thresholds for deformation rate, cumulative deformation, and tilt rate can be represented by the following table.

[0038] Table 2 Thresholds for Quantitative Indicator Risk Level Classification

[0039] After calculating the initial membership vector, the initial membership vector is normalized to finally obtain the membership vector of each quantitative indicator to each risk level in the preset risk level.

[0040] For the qualitative indicators corresponding to the indicator layers B1 ground settlement susceptibility, B2 building structural properties, and B4 external construction disturbance, based on the experience of experts in the field of building engineering, industry standards, and engineering practice data, and according to the pre-set qualitative indicator risk membership assignment table, each qualitative indicator is directly assigned a fixed membership vector to a pre-set risk level. The pre-set qualitative indicator risk membership assignment table is shown in Table 3 below: Table 3. Qualitative Indicator Risk Membership Assignment Table ([Very Low Risk, Low Risk, Medium Risk, High Risk])

[0041] It should be noted that the dimension of the membership vector is consistent with that of the evaluation set, so that the fuzzy information contained in the qualitative indicators can be quantitatively expressed.

[0042] In step S103 of some embodiments, the Analytic Hierarchy Process (AHP) is a systematic analysis method that hierarchically represents a complex decision-making problem with multiple objectives and criteria, and determines the relative importance weights of each indicator by constructing a judgment matrix. In this embodiment, fuzzy analytic hierarchy process is used, introducing a fuzzy consistency matrix to handle fuzziness in the assessment. The indicator weight can be a quantitative value representing the importance of each level indicator relative to its corresponding indicator at the next higher level; a larger weight value indicates a greater impact of the indicator on the assessment result. The criterion layer weight vector can be a vector composed of the weight values ​​of each dimension of the criterion layer relative to the target layer, reflecting the degree of influence of the four dimensions on the building deformation risk level. The indicator layer weight vector can be a vector composed of the weight values ​​of each indicator at the indicator layer relative to the corresponding criterion layer dimension, reflecting the degree of influence of each specific indicator on its respective criterion layer dimension.

[0043] In some embodiments, the weights of indicators at each level are constructed based on the analytic hierarchy process (AHP) to obtain the weight vectors of the criterion layer and the indicator layer, including: Construct initial fuzzy judgment matrices for each level of the criterion layer relative to the target layer and for each level of the indicator layer relative to the corresponding criterion layer; Each initial fuzzy judgment matrix is ​​transformed into a fuzzy consistency matrix; The weight vectors of each level are obtained by summing the rows of each fuzzy consistency matrix and then normalizing them. The weight vectors of the criterion layer and the weight vectors of each index layer are obtained respectively. For each fuzzy consistency matrix, a consistency check is performed using the fuzzy consistency ratio. If the fuzzy consistency ratio is less than a preset threshold, the matrix is ​​determined to meet the consistency requirements.

[0044] The specific implementation method is as follows: First, initial fuzzy judgment matrices for each level are constructed. Based on the 1-9 fuzzy scaling method, the relative importance of the criteria layer relative to the target layer and each indicator layer relative to its corresponding criteria layer is scored, and the average score is used to form the original fuzzy judgment matrices for each level. ,in This indicates the degree of importance of indicator i relative to indicator j, satisfying the following condition: =1 / ,and =1.

[0045] Table 41-9 Scoring Criteria for Fuzzy Scaling Method

[0046] Secondly, each initial fuzzy judgment matrix is ​​transformed into a fuzzy consistency matrix. For an n-order initial fuzzy judgment matrix... Through formula The fuzzy consistency matrix is ​​calculated. This is to eliminate logical inconsistencies in the judgment matrix.

[0047] Next, the weights of each level of indicators are calculated: by summing the rows of each fuzzy consistency matrix, the weights are obtained. After normalization, the weight vectors of each level are obtained. The criterion layer weight vectors are obtained respectively. and the weight vectors of each indicator layer .

[0048] Finally, a consistency check is performed. The fuzzy consistency ratio (CR) is used to check the rationality of each fuzzy consistency matrix. If CR < 0.1, the matrix is ​​deemed to meet the consistency requirements. If CR ≥ 0.1, the relative importance of the indicators needs to be re-scored and the judgment matrix needs to be adjusted until the consistency requirements are met.

[0049] In step S104 of some embodiments, the fuzzy evaluation matrix can be a matrix formed by arranging the membership vectors of all indicator layers in rows. It is the basic matrix for integrating all quantitative evaluation data of all indicators. The matrix rows correspond to the indicator layers, and the columns correspond to preset risk levels. The fuzzy weighted average method is a fuzzy comprehensive evaluation method that calculates a weighted average of indicator weights and membership values. It can organically integrate the quantitative data and weights of each indicator, reflecting the comprehensive impact of indicators of different importance on the evaluation results. Multi-level fuzzy comprehensive evaluation can be a fuzzy comprehensive evaluation carried out step-by-step according to the indicator system hierarchy. In this embodiment, it is a two-level evaluation—first, a first-level evaluation from the indicator layer to the criterion layer, and then a second-level evaluation from the criterion layer to the target layer. The comprehensive risk membership vector refers to the membership vector corresponding to the target layer, composed of the comprehensive membership values ​​of building deformation risk to each preset risk level, reflecting the comprehensive membership degree of building deformation risk at each level.

[0050] In some embodiments, a fuzzy evaluation matrix is ​​constructed based on the membership vector, and a multi-level fuzzy comprehensive evaluation is performed based on the fuzzy weighted average method according to the criterion layer weight vector and the indicator layer weight vector to obtain the comprehensive risk membership vector of the target layer, including: Based on the membership vectors of each indicator in the indicator layer, construct the fuzzy evaluation matrix corresponding to each criterion layer. The weight vectors of each indicator layer are combined with the fuzzy evaluation matrix of the corresponding criterion layer to obtain the comprehensive risk membership vector of each criterion layer. By combining the comprehensive risk membership vectors of all criterion layers, a fuzzy evaluation matrix for the target layer is constructed. The fuzzy synthesis operation is performed between the criterion layer weight vector and the target layer fuzzy evaluation matrix to obtain the comprehensive risk membership vector of the target layer.

[0051] Specifically, firstly, based on the membership vectors of each indicator in the indicator layer, fuzzy evaluation matrices corresponding to each criterion layer are constructed. The membership vectors of all indicators under the same criterion layer are arranged in rows to form a fuzzy evaluation matrix with dimension m×4 (m is the number of indicators in the indicator layer under the corresponding criterion layer). The matrix rows correspond to indicators, and the columns correspond to the preset risk levels V={V1 (extremely low risk), V2 (low risk), V3 (medium risk), V4 (high risk)}.

[0052] Secondly, fuzzy synthesis is performed on the weight vectors of each indicator layer and the fuzzy evaluation matrix of the corresponding criterion layer. Based on the fuzzy weighted average method, the weight vectors of the indicator layer and the fuzzy evaluation matrix of the corresponding criterion layer are weighted to obtain the comprehensive risk membership vector of each criterion layer, realizing the first-level fuzzy comprehensive evaluation from the indicator layer to the criterion layer. Specifically, for the i-th criterion layer Bi, the corresponding indicator layer weight vector WBi is multiplied with the fuzzy evaluation matrix RBi to obtain the comprehensive risk membership vector Bi=wBi*RBi=(bi1,bi2,bi3,bi4) of the criterion layer, where i=1,2,3,4, * denotes fuzzy weighted average operation, and bi1 to bi4 are the membership values ​​of criterion layer Bi for extremely low risk, low risk, medium risk, and high risk, respectively.

[0053] Then, by combining the comprehensive risk membership vectors of all criterion layers, a fuzzy evaluation matrix for the target layer is constructed: the comprehensive risk membership vectors of each criterion layer are arranged in rows to form a 4×4 fuzzy evaluation matrix R for the target layer. In this matrix, B1 is the membership vector of ground settlement susceptibility, B2 is the membership vector of building structural attributes, B3 is the membership vector of InSAR deformation monitoring, and B4 is the membership vector of external construction disturbance. The matrix rows correspond to the criterion layers, and the columns correspond to the preset risk levels.

[0054] Finally, based on the fuzzy weighted average method, the weight vector of the criterion layer and the fuzzy evaluation matrix of the target layer are weighted and calculated to obtain the comprehensive risk membership vector of the target layer A=WB*R=(a1, a2, a3, a4), realizing the two-level fuzzy comprehensive evaluation from the criterion layer to the target layer, where a1 to a4 are the membership values ​​of the target layer for extremely low risk, low risk, medium risk and high risk, respectively.

[0055] In step S105 of some embodiments, the maximum membership principle can be a key principle for determining the category to which the evaluation object belongs in fuzzy comprehensive evaluation, that is, selecting the category corresponding to the element with the largest value in the membership vector of the evaluation object as the final category to which the evaluation object belongs. The final deformation risk level can be the final assessment result of the building deformation risk, that is, the actual deformation risk level of the building determined from the preset four risk levels of extremely low, low, medium and high.

[0056] In some embodiments, based on the principle of maximum membership, the final deformation risk level of the building is determined from the comprehensive risk membership vector of the target layer, including: The risk level corresponding to the maximum value in the target layer's comprehensive risk membership vector is determined as the final deformation risk level of buildings in the ground subsidence area.

[0057] For example, after obtaining the target layer comprehensive risk membership vector A=WB*R=(a1, a2, a3, a4), based on the principle of maximum membership, the preset risk level corresponding to the element with the largest value in the target layer comprehensive risk membership vector is selected and determined as the final deformation risk level of the building in the ground settlement area.

[0058] In an exemplary embodiment, a 5-story mixed-structure (brick-concrete structure) residential building located in a high-risk area for ground settlement is selected as the evaluation object. The building is about 4m away from the surrounding deep foundation pit and is significantly affected by construction disturbance. Its foundation parameters are as follows: Building number: C0; B1 Ground settlement susceptibility is high (C11); B2 Building structural attribute is mixed structure (C22); B3 InSAR deformation monitoring data are deformation rate 4 mm / a, cumulative deformation 32 mm, and tilt rate 4.5‰; B4 External construction disturbance is affected (C41).

[0059] First, the weights of the indicators at each level were calculated using the classical Analytic Hierarchy Process (AHP). Five experts in geotechnical and structural engineering were invited to construct initial fuzzy judgment matrices for each level: based on the 1-9 fuzzy scaling method, the relative importance of the indicators in the criterion layer (B) relative to the target layer (A), and the relative importance of the indicators in the B3 sub-indicator layers (C31, C32, C33) relative to the criterion layer B3, were scored. The average scores were then used to form the initial fuzzy judgment matrices for each level. The initial fuzzy judgment matrix for the criterion layer is: R B = The initial fuzzy judgment matrix for the B3 sub-index layer is: R B = Matrix elements This indicates the degree of importance of indicator i relative to indicator j, satisfying the following condition: =1 / ,and =1.

[0060] Secondly, each initial fuzzy judgment matrix is ​​transformed into a fuzzy consistency matrix. For an n-order initial fuzzy judgment matrix... Through formula The fuzzy consistency matrix is ​​calculated. This is to eliminate logical inconsistencies in the judgment matrix.

[0061] Next, the weights of each level of indicators are calculated: by summing the rows of each fuzzy consistency matrix, the weights are obtained. After normalization, the weight vectors of each level are obtained. Wherein, the criterion layer weight vector w B =[0.3902,0.2500,0.1098,0.2500], B3 sub-index layer weight vector w B3 =[0.5556,0.2925,0.1520].

[0062] Finally, a consistency check is performed, using the fuzzy consistency ratio (CR) to test the rationality of each fuzzy consistency matrix. The criterion-level consistency ratio CR... B =0.0038<0.1; B3 sub-indicator consistency ratio CR B3 =0.0032<0.1, both passed the consistency test, and the weight allocation is reasonable.

[0063] Secondly, the membership degree of each indicator to the preset risk level is calculated. For qualitative indicators, based on the preset qualitative indicator risk membership degree assignment table, the membership degree vector corresponding to high susceptibility (C11) is as follows: The hybrid structure (C22) corresponds to Affected by construction (C41) For quantitative indicators, piecewise membership functions based on semi-trapezoidal and triangular distributions are used for calculation. A deformation rate of 4 mm / a corresponds to... The cumulative deformation of 32 mm corresponds to A slope of 4.5‰ corresponds to Then, combining the weight vector of the B3 sub-indicators, the comprehensive membership vector of B3 is calculated as follows: .

[0064] Subsequently, multi-level fuzzy comprehensive evaluation and risk level determination were conducted. The comprehensive membership vectors of each criterion layer were arranged row-wise to construct the target layer fuzzy evaluation matrix:

[0065] By performing a fuzzy weighted average operation between the criterion layer weight vector and this matrix, the comprehensive risk membership vector of the target layer is obtained. Based on the principle of maximum membership, the risk level corresponding to the maximum value of 0.651 in the vector is selected, and the final deformation risk level of the building is determined to be high risk.

[0066] Finally, the case results are analyzed. The building is located in a high-risk area for ground settlement, affected by disturbances from deep foundation pit construction, and its InSAR-monitored deformation index is in the medium-to-high risk range. The method in this application, after comprehensively considering four dimensions of indicators, determined it to be high-risk, which highly matches the actual engineering risk environment, verifying the accuracy and feasibility of the method. The evaluation model in this application can be automated using software such as MATLAB, including modules for AHP weight calculation and quantitative indicator membership degree calculation. It supports batch evaluation of single or multiple buildings, and the model parameters can be flexibly adjusted according to different regional geological conditions and engineering needs, possessing broad engineering application value.

[0067] Please see Figure 3 This application also provides a building deformation risk identification device, which can implement the above-mentioned building deformation risk identification method. The device includes: Module 201 is used to construct a multi-level index system for risk assessment of building deformation in ground settlement areas. The target layer is the assessment of building deformation risk level. Ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance are selected as criteria layers. Indicator layers are set to refine each criteria layer. The quantification module 202 is used to perform membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to the preset risk level. Analysis module 203 is used to construct the weights of indicators at each level based on the analytic hierarchy process, and obtain the weight vectors of the criteria layer and the weight vectors of the indicator layer. The weighting module 204 is used to construct a fuzzy evaluation matrix based on the membership vector, and to perform multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the weight vector of the criterion layer and the weight vector of the index layer, so as to obtain the comprehensive risk membership vector of the target layer. Module 205 is used to determine the final deformation risk level of a building from the comprehensive risk membership vector of the target layer based on the principle of maximum membership.

[0068] The specific implementation method of the building deformation risk identification device is basically the same as the specific implementation method of the building deformation risk identification method described above, and will not be repeated here.

[0069] Thirdly, embodiments of this application provide an electronic device, see [link to relevant documentation]. Figure 4 The diagram shown is a structural schematic of an electronic device provided in this application.

[0070] like Figure 4 As shown, the device includes: Memory 31 is used to store computer programs; Processor 32 is used to execute computer programs; When the processor 32 executes the computer program, it implements the building deformation risk identification method as described in any of the above embodiments.

[0071] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 31 and executed by processor 32 to complete this application. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in an electronic device.

[0072] The processor 32 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0073] The memory 31 can be used to store computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0074] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 4The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.

[0075] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed, implements the building deformation risk identification method of any of the above embodiments.

[0076] It should be understood that the implementation of all or part of the processes in the above-described building deformation risk identification method can also be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described building deformation risk identification method. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the relevant jurisdiction. For example, in some relevant jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0077] Fifthly, embodiments of this application also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the building deformation risk identification method of any of the above embodiments.

[0078] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0079] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. A method for identifying building deformation risks, characterized in that, include: A multi-level index system for assessing building deformation risk in areas of ground settlement is constructed. The building deformation risk level assessment is taken as the target layer, and ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance are selected as the criteria layers. An index layer is set to refine each of the criteria layers. The membership degree vector of each indicator in the indicator layer is obtained by performing membership degree quantification on each indicator to the preset risk level. The weights of indicators at each level are constructed based on the analytic hierarchy process, resulting in the weight vectors of the criteria layer and the indicator layer. A fuzzy evaluation matrix is ​​constructed based on the membership vector, and a multi-level fuzzy comprehensive evaluation is performed based on the fuzzy weighted average method according to the criterion layer weight vector and the index layer weight vector to obtain the comprehensive risk membership vector of the target layer. Based on the principle of maximum membership, the final deformation risk level of the building is determined from the comprehensive risk membership vector of the target layer.

2. The building deformation risk identification method as described in claim 1, characterized in that, The step of performing membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to the preset risk level includes: For the quantitative indicators in the indicator layer, the quantitative indicators include deformation rate, cumulative deformation and tilt rate. First, risk level classification thresholds are set for the deformation rate, cumulative deformation and tilt rate respectively. Then, a piecewise membership function is used to map the measured values ​​of the quantitative indicators to the membership degree of each risk level in the corresponding preset risk level. After obtaining the initial membership vector, normalization processing is performed to obtain the membership vector of each quantitative indicator to the preset risk level. For the qualitative indicators in the indicator layer, a membership vector corresponding to a preset risk level is assigned to each qualitative indicator according to the preset qualitative indicator risk membership assignment table.

3. The building deformation risk identification method as described in claim 1, characterized in that, The method of constructing the weights of indicators at each level based on the analytic hierarchy process (AHP) yields the weight vectors of the criterion layer and the indicator layer, including: Construct initial fuzzy judgment matrices for each level of the criterion layer relative to the target layer and for each level of the indicator layer relative to the corresponding criterion layer; Each of the initial fuzzy judgment matrices is transformed into a fuzzy consistency matrix; The fuzzy consistency matrices are summed row by row, and after normalization, the weight vectors of each level are obtained, which are then used to obtain the weight vectors of the criterion layer and the weight vectors of each index layer. The consistency of each fuzzy consistency matrix is ​​checked using a fuzzy consistency ratio. If the fuzzy consistency ratio is less than a preset threshold, the matrix is ​​determined to meet the consistency requirements.

4. The building deformation risk identification method as described in claim 1, characterized in that, The step of constructing a fuzzy evaluation matrix based on the membership vector, and performing a multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the criterion layer weight vector and the indicator layer weight vector to obtain the comprehensive risk membership vector of the target layer includes: Based on the membership vectors of each indicator in the indicator layer, construct the fuzzy evaluation matrix corresponding to each criterion layer. The weight vectors of each indicator layer are combined with the fuzzy evaluation matrix of the corresponding criterion layer to obtain the comprehensive risk membership vector of each criterion layer. By combining the comprehensive risk membership vectors of all criterion layers, a fuzzy evaluation matrix for the target layer is constructed. The fuzzy synthesis operation is performed between the criterion layer weight vector and the target layer fuzzy evaluation matrix to obtain the comprehensive risk membership vector of the target layer.

5. The building deformation risk identification method as described in claim 1, characterized in that, The index layers for ground subsidence susceptibility include high susceptibility, medium susceptibility, and low susceptibility. The index layer of building structural attributes includes reinforced concrete, mixed structure, brick-wood structure, and simple structure; The InSAR deformation monitoring index layer includes deformation rate, cumulative deformation, and tilt rate; The index layer for external construction disturbance includes yes and no.

6. The building deformation risk identification method as described in claim 1, characterized in that, The determination of the final deformation risk level of a building from the comprehensive risk membership vector of the target layer based on the principle of maximum membership includes: The risk level corresponding to the maximum value in the target layer's comprehensive risk membership vector is determined as the final deformation risk level of buildings in the ground subsidence area.

7. A building deformation risk identification device, characterized in that, include: The module is used to construct a multi-level index system for assessing building deformation risk in areas of ground settlement. The target layer is the assessment of building deformation risk level. The criteria layers are ground settlement susceptibility, building structural properties, InSAR deformation monitoring, and external construction disturbance. The index layers are set to refine each of the criteria layers. The quantification module is used to perform membership quantification on each indicator in the indicator layer to obtain the membership vector of each indicator to the preset risk level. The analysis module is used to construct the weights of indicators at each level based on the analytic hierarchy process (AHP) to obtain the weight vectors of the criteria layer and the indicator layer. The weighting module is used to construct a fuzzy evaluation matrix based on the membership vector, and to perform multi-level fuzzy comprehensive evaluation based on the fuzzy weighted average method according to the criterion layer weight vector and the index layer weight vector to obtain the comprehensive risk membership vector of the target layer. The determination module is used to determine the final deformation risk level of the building from the comprehensive risk membership vector of the target layer based on the principle of maximum membership.

8. An electronic device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the building deformation risk identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the building deformation risk identification method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, implement the building deformation risk identification method as described in any one of claims 1 to 6.

Images