A building structure safety risk assessment system

Abstract

The application discloses a kind of building structure safety risk assessment systems, it is related to building engineering technical field, the system includes building mechanics parameter acquisition module, rigidity index analysis module, image feature extraction module, comprehensive analysis module, risk assessment module, the present application is by comprehensively considering the mechanics parameter and image feature of building structure, reflect the mechanical properties and damage degree of building structure under the action of load, and with the concrete surface feature image collected Comparative analysis, extract the damage condition and image feature value of building structure surface, by comprehensive analysis module, rigidity index and loss function are fused, loss feature value is obtained, and then the quantitative evaluation of building structure safety risk is realized, this kind of comprehensive evaluation method not only improves the comprehensiveness and accuracy of evaluation result, also provides powerful data support for subsequent risk control and repair measures.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building engineering, in particular to a building structure safety risk assessment system. BACKGROUND

[0002] In the whole life cycle of building structure, from design, construction to use and maintenance, the structure safety needs to be continuously monitored and evaluated. Due to the frequent occurrence of natural disasters and the increasingly prominent problems of building aging, the importance of building structure safety risk assessment is increasingly significant. The traditional building structure safety evaluation method mainly relies on manual inspection and experience judgment, which has many limitations and cannot meet the growing demand for building structure safety evaluation.

[0003] At present, in the determination of rigidity index, the traditional method only considers single factor and simple mechanical relationship for calculation, which leads to inaccurate calculation of rigidity index and cannot fully reflect the actual rigidity and deformation resistance of building structure under complex working conditions. For the calculation of loss function, based on simple image features for analysis, the multiple feature information of concrete surface and the mechanical performance parameters of building structure are not fully combined, so that the loss function cannot accurately quantify the surface damage degree of building structure and its influence on the overall safety, resulting in that the safety evaluation result of building structure is not comprehensive and accurate, and it is difficult to find potential safety risks in advance. SUMMARY

[0004] The purpose of the present application is to make up for the shortcomings of the prior art, and provide a building structure safety risk assessment system. The system can comprehensively evaluate the safety state of building structure under the action of earthquake by combining the analysis method of rigidity index and loss function. At the same time, the information of structure surface damage is further supplemented by analyzing the concrete surface features through the image feature extraction module, which can more comprehensively reflect the real state of building structure and reduce the evaluation error caused by single data source.

[0005] The present application provides the following technical solutions to solve the above technical problems:

[0006] A building structure safety risk assessment system, the system comprises a building mechanics parameter acquisition module, a rigidity index analysis module, an image feature extraction module, a comprehensive analysis module and a risk assessment module.

[0007] The building mechanics parameter acquisition module is used to collect building mechanics parameters in each monitoring area of ​​the building structure, including: seismic load value, ultimate strength, and steel reinforcement damage degree value. Specifically: seismic load value acquisition utilizes a seismograph to monitor the dynamic response data of the building structure under seismic action in real time, including acceleration, velocity, and displacement parameters, and obtains the seismic load value through integration calculation; ultimate strength acquisition uses stress sensors and strain sensors to monitor the strength changes of building components in real time; steel reinforcement damage degree value acquisition detects the number of damaged steel bars in the building structure and calculates the degree of steel reinforcement damage.

[0008] The rigidity index analysis module calculates the rigidity index based on the building mechanics data collected by the building mechanics parameter acquisition module.

[0009] The image feature extraction module is responsible for acquiring concrete surface feature images and inputting them into the safety monitoring model. After image enhancement processing, image feature values ​​are obtained, and a loss function is calculated based on the image feature values. The safety monitoring model construction process is as follows:

[0010] Image Sample Collection and Annotation: Collect image samples of concrete surface features, including images of different crack types, varying degrees of damage, and images under normal conditions, to form a sample set. Among them I j Let N represent the j-th image, and N be the total number of samples. The images in the sample set are labeled, including crack type, crack length, width, and number, forming a label set. Among them l j Represents image I j Corresponding annotation information;

[0011] Feature extraction network design: A convolutional neural network (CNN) is constructed as the architecture for a security monitoring model. This network contains multiple convolutional layers, pooling layers, and fully connected layers. Specifically, for an input image I, the output feature map F of the l-th convolutional layer... l for: Where F l-1 It is the output feature map of the previous layer. W represents the convolution operation. l b is the convolution kernel weight matrix of the l-th layer. l The term is the bias term of the l-th layer, and f(·) is the activation function; pooling layer: for the input feature map F l The output feature map F′ after pooling l For: F′ l =Pooling(F l ), where Pooling(·) represents the pooling operation; Fully connected layer: unfolds the feature map after processing by multiple convolutional and pooling layers into a one-dimensional vector, connects it to the fully connected layer, and the output of the fully connected layer is Y = f(W fcX+b fc where X is the unfolded eigenvector, W fc is the weight matrix of the fully connected layer, b fc is the bias term of the fully connected layer, and f(·) is the activation function.

[0012] Model training: define the loss function J(θ) of the model, and use the combination form of cross-entropy loss function and mean square error loss function, that is, J(θ) = λ1J ce (θ) + λ2J mse (θ), where θ represents the parameters of the feature extraction network, λ1 and λ2 are weight coefficients for balancing the contributions of the two loss functions, wherein the cross-entropy loss function J ce (θ) is used for classification task, that is, the classification of crack type, and the calculation formula is C is the number of categories, y ji is an indicator variable, N is the total number of samples, y j = 1 when the image I ki belongs to category i, otherwise y ji = 0, p ji (θ) is the probability that the model predicts that the image I j belongs to category i, and the mean square error loss function J mse (θ) is used for regression task, that is, the prediction of crack length and width parameters, and the calculation formula is where M is the number of regression tasks, z jm is the actual value of the mth regression target of the image I j , q jm (θ) is the corresponding value predicted by the model, and the network parameters θ are updated multiple times to minimize the loss function, and a safety monitoring model is obtained.

[0013] The rigidity index calculated by the rigidity index analysis module and the loss function of the image feature extraction module are fused by the comprehensive analysis module to obtain a loss feature value.

[0014] The risk assessment module compares the loss feature value obtained by the comprehensive analysis module with a damage feature value threshold to output a building structure damage instruction.

[0015] Further, the building mechanics parameter acquisition module collects the earthquake load value by using a seismic monitor to accurately measure the load value borne by the building structure under the action of an earthquake, and capture the load change generated by seismic waves of different intensities and frequencies, i.e., the acceleration time sequence a(t) of the seismic wave collected by the seismic monitor, where t represents time. The displacement d(t) is calculated by twice integrating the acceleration, the velocity is calculated by once integrating the acceleration, and the displacement d(t) = ∫v(t)dt+d0, where d0 is the initial displacement. The earthquake load value P e is related to the displacement, velocity, and acceleration as follows: P e = k s d(t) + c s v(t) + m s a(t), where k s is the stiffness coefficient of the structure, c s is the damping coefficient of the structure, and m s is the mass of the structure.

[0016] Further, the building mechanics parameter acquisition module collects the ultimate strength by using a stress sensor and a strain sensor to monitor the stress σ(T) and strain ∈(T) of the building structure under the load T, to evaluate the ultimate strength where k is the strength coefficient, reflecting the influence of strain on the ultimate strength, and t is the monitoring time period.

[0017] Further, the building mechanics parameter acquisition module collects the steel bar damage degree value by detecting the number of damaged steel bars in the building structure, and calculating the steel bar damage degree value D r = k where N d is the number of damaged steel bars, and N t is the total number of steel bars.

[0018] Further, the rigidity index analysis module calculates the rigidity index by comprehensively considering the factors of the earthquake load value, the ultimate strength, and the steel bar damage degree value, to comprehensively reflect the overall rigidity and deformation resistance of the building structure. The rigidity index RI is calculated according to the building mechanics data collected by the building mechanics parameter acquisition module, i.e., where k is the damage coefficient, C s is the structure coefficient, D r is the steel bar damage degree value, f u is the ultimate strength, and P e is the earthquake load value.

[0019] Further, the image feature extraction module inputs the collected concrete surface feature images into the trained safety monitoring model, extracts features through the convolutional layer and pooling layer of the safety monitoring model to obtain multiple feature maps, extracts feature values from the feature maps, and uses the extracted i-th feature value x i , and calculates the loss function L as: where n represents the number of different types of image features, w i is the weight coefficient of the i-th type of image feature, and f i (x i ) is the function representation of the i-th type of image feature.

[0020] Further, the comprehensive analysis module fuses the rigidity index RI calculated by the rigidity index analysis module and the loss function L of the image feature extraction module to obtain the loss feature value LF, and its fusion formula is: where RI min and RI max are respectively the minimum and maximum values of the rigidity index, L min and L max are respectively the minimum and maximum values of the loss function, ω1 and ω2 are fusion weight coefficients, and ω1 + ω2 = 1, which are used to adjust the relative importance of the rigidity index and the loss function in the fusion process.

[0021] Further, the risk assessment module compares the loss feature value LF obtained by the comprehensive analysis module with the damage feature value threshold T, including:

[0022] For the loss feature value exceeding the threshold, that is, LF ≥ T, an instruction for damaged building structure is output;

[0023] For the loss feature value not reaching the threshold, that is, LF < T, an instruction for undamaged building structure is output, and at the same time, the threshold T is adjusted for secondary risk assessment according to factors such as the usage situation, maintenance history, and environmental changes of the building structure, and adjusted to T = T0 × (1 + α u u + α m m + α e e), where T0 is the initial threshold, u, m, and e are respectively the quantization parameters of the usage situation, maintenance history, and environmental changes, and α u , α m , α e are respectively the adjustment coefficients of the usage situation, maintenance history, and environmental changes, which are used to measure the influence degree of different factors on the threshold adjustment.

[0024] Compared with the prior art, this building structure safety risk assessment system has the following beneficial effects:

[0025] One, the application reflects the mechanical properties and damage degree of the building structure under the action of load by comprehensively considering the mechanical parameters and image features of the building structure, and compares and analyzes the collected concrete surface feature images, extracts the damage condition of the building structure surface and the image feature value, fuses the rigidity index and the loss function through a comprehensive analysis module, obtains the loss feature value, and then realizes the quantitative evaluation of the safety risk of the building structure, and the comprehensive evaluation method not only improves the comprehensiveness and accuracy of the evaluation result, but also provides strong data support for subsequent risk control and repair measures.

[0026] Two, the system can monitor various parameters and image information of the building structure in real time, and accurately judge the safety risk of the building structure in time according to the comparison of the loss feature value and the threshold value, and the real-time risk early warning capability greatly improves the safety of the building structure, effectively prevents the occurrence of major safety accidents.

[0027] Other advantages, objects and features of the present application will be set forth in part in the following specification, and in part will be apparent from the study of the following specification, or can be learned from the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0029] Figure 1 It is a flow chart of the operation of a building structure safety risk assessment system;

[0030] Figure 2 It is a flow chart of the construction of a safety monitoring model in a building structure safety risk assessment system. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0032] Embodiment one

[0033] This embodiment focuses on the application of building structure safety risk assessment system in large commercial buildings, and elaborates in detail how each module of the system works in complex conditions, realizes accurate monitoring and analysis of the mechanical properties and damage status of building structures, and finally achieves comprehensive, real-time and reliable assessment of building structure safety risk, providing practical scientific basis and technical support for safety management of large commercial buildings.

[0034] In specific implementation, large commercial buildings have large scale, complex structure system and high density of personnel flow, which determines their high requirements for structural safety performance. Real-time monitoring of the performance changes of building structures under various complex conditions can timely discover potential safety hazards, provide strong support for taking effective prevention and response measures, and ensure that large commercial buildings always maintain safe and reliable operation state in the whole life cycle. First, the dynamic response of building structure under earthquake is accurately obtained. High-precision seismic monitoring instruments are deployed in the middle of the building. The seismic monitoring instrument records the acceleration time series a(t) of seismic wave in real time with high frequency and high precision. When integrating the acceleration, the velocity v(t) is calculated by first integration, according to the integral principle, v(t) = ∫a(t)dt + v0, since the building is in a static state before the earthquake occurs, the initial velocity v0 is set to 0, and the displacement d(t) is obtained by twice integration of the velocity, the calculation formula is d(t) = ∫v(t)dt + d0, similarly, the initial displacement d0 of the building is also 0. Through these integral operations, the motion trajectory and deformation of building structure under the action of earthquake can be accurately restored. The seismic load value P e There is a clear relationship between displacement d(t), velocity v(t) and acceleration a(t), that is, P e = k s d(t) + c s v(t) + m s a(t), where the stiffness coefficient k s of the structure is an important indicator of the deformation resistance of the building structure, the damping coefficient c s of the structure reflects the energy dissipation capacity of the building structure in the vibration process, and the mass m s of the structure is the cumulative mass of various building materials used by the building structure. By accurately measuring and calculating these parameters, the dynamic changes of the seismic load value with time can be accurately calculated, providing key data support for subsequent rigidity index calculation.

[0035] Then, stress sensors and strain sensors are pre-embedded in the main concrete components and steel structural components of the building structure, forming a comprehensive and detailed monitoring network. In the concrete components, the sensors can sense the stress and strain state of the concrete under various load actions in real time. During the entire service life of the building, these sensors continuously monitor the stress and strain state of the building components under normal use load and extreme load conditions. According to the calculation formula of ultimate strength where k is the strength coefficient, reflecting the influence of strain on ultimate strength, and t is the monitoring time period. Through long-term data accumulation and analysis, the change trend of the ultimate strength of the building structure can be accurately mastered, and the possible attenuation or deterioration of the ultimate strength can be timely discovered, providing important basis for evaluating the safety of the building structure. For the reinforcement in the building structure, the total reinforcement quantity N is accurately counted according to the design drawings and construction records of the building structure t , and the reinforcement damage degree value is accurately calculated according to the calculation formula of reinforcement damage degree value , providing reliable data support for evaluating the safety of the building structure. On the facade of the building, high-definition image acquisition devices are installed, and image acquisition points are set on the surface of the internal main load-bearing structure to monitor the surface condition of the structure under internal load action. These devices are connected to the data processing center through wireless transmission to ensure that images can be transmitted in a timely and stable manner. Automatic shooting of concrete surface images builds a large and rich image sample set At the same time of image acquisition, each image in the sample set is labeled in detail, and the labeling content covers crack types. Through analysis of crack morphology, direction, etc., it can be accurately judged whether the crack belongs to horizontal, vertical, diagonal crack or other complex morphology crack. The crack length and crack width are accurately measured, and the crack quantity is counted to form a complete labeled set L = {l j} j＝1 , which provides accurate reference for subsequent safety monitoring model training and image feature analysis.

[0036] Subsequently, the collected concrete surface feature images are input into the safety monitoring model for image enhancement processing. In the histogram equalization process, for the gray level range [0, L-1] of the image (where L is the number of gray levels), the gray histogram h(i) (i = 0, 1, …, L-1) of the original image is counted, and the gray value of the image is redistributed according to the formula (where M is the total number of image pixels) to make the gray distribution of the image more uniform, thereby significantly enhancing the contrast of the image and highlighting the fine features such as cracks and peeling on the concrete surface. The image after image enhancement processing is sent to the convolution layer and pooling layer of the safety monitoring model for deep feature extraction. In the convolution layer, for the input image I, each layer of the convolution layer is convolved with the convolution kernel and the output feature map F l-1Convolution operation is performed and a bias term b is added l After the processing of the activation function f(·), the output feature map of the current layer is obtained The convolution kernel weight matrix W l Different features of the image are extracted in the convolution process, and the max-pooling is used in the pooling layer to down-sample the feature map output by the convolution layer. For the input feature map F l , the output feature map F' after pooling is l = Pooling(F l ), the pooling operation can effectively reduce the size of the feature map, reduce the amount of calculation, and at the same time preserve the main feature information of the image. After layer-by-layer processing of multiple convolution layers and pooling layers, the feature map is unfolded into a one-dimensional vector and connected to the fully connected layer. The number of neurons in the fully connected layer is determined according to the task type and data complexity, and the final result is output by calculating Y = f(W fc X + b fc ) (where X is the unfolded feature vector, W fc is the weight matrix of the fully connected layer is the bias term of the fully connected layer, and f(·) is the activation function). Key feature values are extracted from the processed feature map, i.e. the i-th extracted feature value is x i These feature values include the length, width, depth of the crack, the distribution density of the crack, the area and depth of the spalling area, and its position in the image, etc. According to these key feature values, the loss function is calculated where n represents the number of different types of image features, w i is the weight coefficient of the i-th image feature, reflecting the importance of different image features to the safety evaluation of the building structure, f i (x i ) is the function expression of the i-th image feature. By accurately calculating the loss function, the damage degree of the concrete surface and its influence on the overall safety of the building structure can be quantified.

[0037] According to the rich and accurate data collected by the building mechanics parameter acquisition module, the rigidity index RI is calculated, and the calculation formula of the rigidity index is Where the ultimate strength f u is calculated by the long-term monitoring data of the strain sensor, which reflects the maximum bearing capacity of the building structure under load; the steel damage degree value D r is determined by local damage detection, which reflects the damage condition of the steel in the building structure, and the damage of the steel will weaken the overall performance of the structure; the seismic load value P e is measured and calculated in real time by the earthquake monitor when the earthquake occurs, which is the external dynamic load borne by the building structure under the action of the earthquake; the damage coefficient k quantifies the influence degree of the steel damage on the rigidity index, and Cs is a structure coefficient, by calculating a rigidity index that accurately reflects the overall rigidity and deformation resistance of the building structure, providing important structural mechanical performance indicators for subsequent risk assessment, based on the obtained key eigenvalues, according to the loss function calculation formula , for different types of image features such as cracks, spalling, holes, etc., according to their respective eigenvalues and carefully determined weight coefficients, accurately calculate their contribution to the loss function, through the comprehensive calculation of various image features, get a loss function value that comprehensively reflects the damage degree of concrete surface and its influence on the overall safety of building structure, fuse the rigidity index RI and the loss function L through the fusion formula , get the loss eigenvalue LF, where RI min and RI max are the minimum and maximum values of the rigidity index respectively, which are determined by theoretical analysis and simulation calculation of building structures under different working conditions, reflecting the value range of the rigidity index of building structure, L min and L max are the minimum and maximum values of the loss function respectively, which are obtained by in-depth analysis and calculation of sample images, reflecting the value range of the loss function under different damage degrees; ω1 and ω2 are fusion weight coefficients, and satisfy ω1+ω2=1, used to accurately adjust the relative importance of rigidity index and loss function in the fusion process, according to the type, use environment, importance of building structure, etc., reasonably determine the value of ω1 and ω2, ensure that the loss eigenvalue can accurately reflect the safety of building structure.

[0038] Finally, the calculated loss eigenvalue LF is strictly compared with the preset damage eigenvalue threshold T, when LF≥T, the system determines that the building structure is damaged, and outputs the building structure damage instruction immediately, when LF<T, the system determines that the building structure is not damaged, and outputs the building structure undamaged instruction, at the same time, according to the use of building structure (such as use time, use frequency, load change, etc. Quantitative parameters u), maintenance history (such as maintenance times, maintenance degree, last maintenance time interval, etc. Quantitative parameters m), environmental changes (such as temperature change amplitude, humidity change, earthquake activity frequency, etc. Quantitative parameters e) and other factors adjust the threshold T, the adjustment formula is T=T0×(1+α u u+α m m+α e e), where T0 is the initial threshold, α u , α m , α e are the adjustment coefficients of use, maintenance history and environmental change respectively, and according to the secondary evaluation results, real-time adjust the risk assessment threshold, provide real-time data for building structure safety risk assessment.

[0039] In summary, the application of the building structure safety risk assessment system in large commercial buildings fully demonstrates the collaborative working ability and effectiveness of each module of the system, from building mechanics parameter collection to image feature extraction, to accurate calculation analysis and timely risk assessment decision, realizing comprehensive and real-time monitoring and evaluation of the safety condition of the large commercial building structure, ensuring the accuracy and reliability of the evaluation results, and providing a solid technical guarantee for the safe operation of large commercial buildings.

[0040] It is apparent for a person skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all respects as illustrative and not restrictive, the scope of the present application being defined by the appended claims rather than the above description, and all changes falling within the meaning and range of equivalency of the elements of the claims are intended to be embraced therein. Any reference signs in the claims should not be construed as limiting the claims to the figures in which the reference signs are used.

Claims

1. A building structure safety risk assessment system, characterized by, The system comprises a building mechanics parameter acquisition module, a rigidity index analysis module, an image feature extraction module, a comprehensive analysis module, and a risk assessment module. The building mechanics parameter acquisition module is configured to acquire building mechanics parameters in each monitoring area of the building structure, including seismic load values, ultimate strength values, and steel damage degree values, wherein: The seismic load values are acquired by using a seismograph to monitor the dynamic response of the building structure under the action of an earthquake in real time, including acceleration, speed, and displacement parameters, and the seismic load values are obtained by integral operation; The ultimate strength values are acquired by using stress sensors and strain sensors to monitor the strength changes of the building components in real time; The steel damage degree values are acquired by detecting the number of damages of the steel bars in the building structure and calculating the steel damage degree values; The rigidity index analysis module calculates the rigidity index RI according to the building mechanics data collected by the building mechanics parameter collection module, Wherein k is the damage coefficient, C s is the structure coefficient, D r is the reinforcement damage degree value, f u is the ultimate strength, P e is the seismic load value; The image feature extraction module is responsible for acquiring concrete surface feature images and inputting them into a safety monitoring model, obtaining image feature values through image enhancement processing, calculating a loss function based on the image feature values, and constructing the safety monitoring model as follows: I. Image sample collection and labeling: collect concrete surface feature image samples, including different crack types, different damage levels, and normal state images, to form a sample set, label the images in the sample set, including crack type, crack length, width, and number, to form a labeled set; II. Constructing feature extraction network: adopt convolutional neural network (CNN) as the architecture of the safety monitoring model, which contains multiple convolutional layers, pooling layers and fully connected layers. The convolutional layer: for the input image I, the output feature map F l of the lth convolutional layer; the pooling layer: for the feature map F l , the output feature map F′ l after pooling; the fully connected layer: the feature map processed by multiple convolutional layers and pooling layers is unfolded into a one-dimensional vector and connected to the fully connected layer; III. Model training: define the loss function J(θ) of the model, adopt the combination form of cross-entropy loss function J ce (θ) and mean square error loss function J mse (θ), J(θ) = λ1J ce (θ) + λ2J mse (θ), where θ represents the parameters of the feature extraction network, λ1 and λ2 are weight coefficients, used to balance the contribution of cross-entropy loss function J ce (θ) and mean square error loss function J mse (θ), wherein the cross-entropy loss function J ce (θ) is used for classification task, i.e. classification of crack type, and the calculation formula is C is the number of categories, y ji is an indicator variable, N is the total number of samples, y j = 1 when the image I ji belongs to category i, otherwise y ji = 0, p ji (θ) is the probability that the model predicts that the image I j belongs to category i, the mean square error loss function J mse (θ) is used for regression task, i.e. prediction of crack length and width parameters, and the calculation formula is where M is the number of regression tasks, z jm is the actual value of the mth regression target of the image I j , q jm (θ) is the corresponding value predicted by the model, the network parameters θ are trained and updated multiple times to minimize the loss function J(θ), and a trained safety monitoring model is obtained. The comprehensive analysis module is configured to combine the rigidity index RI calculated by the rigidity index analysis module and the loss function L of the image feature extraction module, wherein n represents the number of different types of image features, w i is a weight coefficient of the i-th image feature, f i (x i ) is a function representation of the i-th image feature, x i is the i-th feature value x i extracted; The loss feature value LF is obtained by fusion, and a fusion formula thereof is: Wherein, RI min and RI max are the minimum value and the maximum value of the rigidity index respectively, L min and L max are the minimum value and the maximum value of the loss function respectively, ω1 and ω2 are fusion weight coefficients, and ω1+ω2=1 is satisfied, for adjusting the relative importance of the rigidity index and the loss function in the fusion process; The risk assessment module compares the loss feature values obtained by the comprehensive analysis module with the damage feature value threshold to output a building structure damage instruction.

2. The building structure safety risk assessment system according to claim 1, wherein The building mechanics parameter acquisition module collects the earthquake load value by using a seismic monitor, accurately measures the load value borne by the building structure under the action of an earthquake, and captures the load changes generated by seismic waves of different intensities and frequencies, i.e., the seismic wave acceleration time sequence collected by the seismic monitor is a(t), where t represents time, the displacement d(t) is calculated by twice integrating the acceleration, including once integrating the acceleration to obtain the velocity, and then once integrating the velocity to obtain the displacement d(t)=∫v(t)dt+d0, where d0 is an initial displacement, and the earthquake load value P e is related to the displacement, velocity, and acceleration as follows: P e =k s d(t)+c s v(t)+m s a(t), where k s is a stiffness coefficient of the structure, c s is a damping coefficient of the structure, and m s is a mass of the structure.

3. The building structure safety risk assessment system according to claim 1, wherein, The building mechanics parameter acquisition module acquires the limit strength by stress sensors and strain sensors, monitors the stress σ(T) and strain ∈(T) state of the building structure under the load T, and evaluates the limit strength wherein k is a strength coefficient, reflecting the influence of strain on the limit strength, and t is the monitoring time period.

4. The building structure safety risk assessment system according to claim 1, wherein, The building mechanics parameter acquisition module acquires the steel bar damage degree value by detecting the damage number of the steel bar in the building structure, and calculates the steel bar damage degree value D r For Wherein N d is the number of damaged steel bars, N t is the total number of steel bars.

5. The building structural safety risk assessment system according to claim 1, wherein, The image feature extraction module inputs the acquired concrete surface feature images into the trained safety monitoring model, extracts features through the convolution layer and the pooling layer of the safety monitoring model, and obtains multiple feature maps to extract feature values from the feature maps.

6. The building structural safety risk assessment system according to claim 1, wherein, The risk assessment module compares the loss feature values LF obtained by the comprehensive analysis module with the damage feature value threshold T, including: If the loss feature value exceeds the threshold, i.e., LF≥T, output a building structure damage instruction; For the loss feature value does not reach the threshold value, that is, LF < T, output the instruction that the building structure is not damaged, and adjust the threshold value T according to the use of the building structure, the maintenance history, and the environmental change factors to carry out secondary risk assessment, and the adjustment is T = T0 × (1 + α u u+α m m+α e e), wherein T0 is an initial threshold value, u, m and e are quantitative parameters of the use, the maintenance history and the environmental change respectively, and α u 、α m 、α e are adjustment coefficients of the use, the maintenance history and the environmental change respectively, and are used to measure the influence degree of different factors on the threshold value adjustment.

Images