Historical building dynamic risk assessment method and system

Abstract

The invention discloses a historical building dynamic risk assessment method and system, and relates to the technical field of risk assessment, and the method comprises the steps: carrying out defect space-time change trajectory marking according to defect space distribution density data, obtaining defect space-time change trajectory data, carrying out defect evolution trend estimation based on the defect space-time change trajectory data, and carrying out risk assessment. Defect evolution trend data is obtained, historical building risk grade reference evaluation is carried out according to the defect evolution trend data, and risk grade reference data is obtained; performing environmental impact factor identification on the defect evolution trend data according to historical building environmental monitoring data to obtain an environmental association impact factor, and performing risk impact dynamic correction on the risk level reference data to obtain risk impact correction data; and performing dynamic risk assessment model construction on the risk influence correction data to obtain a historical building dynamic risk assessment model. The historical building dynamic risk assessment method has the effect of improving historical building dynamic risk assessment efficiency.

Description

Technical Field

[0001] This application relates to the field of risk assessment technology, and in particular to a method and system for dynamic risk assessment of historical buildings. Background Technology

[0002] With the acceleration of urbanization, more and more historical buildings are gradually becoming an important part of cultural heritage. Due to long-term natural erosion, environmental changes, aging, and human damage, historical buildings face varying degrees of damage and risks. In order to protect and inherit these valuable cultural resources, it is particularly important to reasonably and timely assess the dynamic risks of historical buildings. However, existing risk assessment methods for historical buildings still have many limitations, and innovative technologies are urgently needed to improve the accuracy, reliability, and real-time nature of the assessment.

[0003] In related technologies, traditional dynamic risk assessment methods for historical buildings rely on manual inspections and isolated sensors. The data is discontinuous in time and incomplete in space, making it impossible to construct a complete data model reflecting the overall state of the building and its spatiotemporal evolution. This results in a weak assessment foundation. Secondly, risk assessments are mostly based on obvious defects that have been discovered, lacking the ability to predict potential defects and micro-changes. Furthermore, they heavily rely on expert experience, making them difficult to quantify and standardize. Different assessors may reach significantly different conclusions, resulting in insufficient consistency, objectivity, and foresight in the risk assessment results. They also fail to fully consider the dynamic coupling effect between environmental factors and the evolution of structural defects, separating the analysis of structural response from environmental loads. This makes it impossible to accurately reflect the impact mechanism of environmental stress on the cumulative fatigue damage of building materials and the accelerated propagation of defects, thus reducing the efficiency of dynamic risk assessment for historical buildings. There are areas for improvement. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this application provides a method and system for dynamic risk assessment of historical buildings.

[0005] Firstly, this application provides a dynamic risk assessment method for historical buildings, comprising the following steps: Step S1: Collect historical building structure data through monitoring equipment to obtain historical building structure monitoring data; perform intelligent identification and analysis of structural defects on the historical building structure monitoring data to obtain historical building structure defect identification data; and perform spatial distribution density analysis between defects based on the historical building structure defect identification data to obtain defect spatial distribution density data. Step S2: Mark the spatiotemporal change trajectory of defects based on the spatial distribution density data of defects to obtain spatiotemporal change trajectory data of defects. Estimate the evolution trend of defects based on the spatiotemporal change trajectory data of defects to obtain evolution trend data of defects. Conduct a risk level benchmark assessment of historical buildings based on the evolution trend data of defects to obtain risk level benchmark data of risks. Step S3: Obtain historical building environmental monitoring data, identify environmental impact factors based on the defect evolution trend data according to the historical building environmental monitoring data, obtain environmentally related impact factors, and dynamically correct the risk level benchmark data based on the environmentally related impact factors to obtain risk impact corrected data; Step S4: Construct a dynamic risk assessment model for the risk impact correction data using an adaptive learning algorithm to obtain a dynamic risk assessment model for historical buildings. Deploy the dynamic risk assessment model for historical buildings on a cloud monitoring platform to perform dynamic risk assessment and early warning for historical buildings.

[0006] Preferably, step S1 includes the following steps: Step S11: Collect historical building structure data through monitoring equipment to obtain historical building structure monitoring data; wherein, the monitoring equipment is deployed at key structural parts of the historical building; Step S12: Perform data preprocessing and fusion on the historical building structure monitoring data to obtain historical building structure fusion data; Step S13: Perform intelligent structural defect identification and analysis on the fused data of historical building structures to obtain structural defect identification data of historical buildings; Step S14: Perform spatial distribution density analysis between defects based on the historical building structural defect identification data to obtain defect spatial distribution density data.

[0007] Preferably, step S2 includes the following steps: Step S21: Mark the spatiotemporal change trajectory of defects in historical building structure monitoring data based on the spatial distribution density data of defects to obtain the spatiotemporal change trajectory data of defects; Step S22: Estimate the defect evolution trend based on the spatiotemporal change trajectory data of defects in historical building structures to obtain defect evolution trend data; Step S23: Perform trend clustering and consistency analysis on the defect evolution trend data to obtain defect evolution clustering data; Step S24: Based on the defect evolution clustering data and defect spatial distribution density data, conduct a risk level benchmark assessment on the historical building structural defect identification data to obtain risk level benchmark data.

[0008] Preferably, step S22 includes the following steps: Step S221: Extract the geometric features of each defect from the structural defect identification data of historical buildings to obtain defect geometric feature data; Step S222: Based on the defect geometric feature data, quantify the structural impact of each defect in the historical building structural defect identification data to obtain the defect structural impact quantification data; Step S223: Based on the spatiotemporal change trajectory data of defects, extract the environmental response of each defect from the historical building structure monitoring data to obtain defect environmental response data; Step S224: Based on the defect environmental response data, perform impact compensation on the defect structure impact quantification data under different environmental conditions to obtain defect-environment structure impact compensation data; Step S225: Estimate the defect evolution trend based on the defect-environment structure influence compensation data to obtain defect evolution trend data.

[0009] Preferably, the impact compensation for the defect structure under different environmental conditions is performed based on the defect environmental response data and the quantitative data of the defect structure's impact, including the following steps: Based on the defective environmental response data, key parameters are analyzed under different environmental conditions to obtain environmental condition parameter analysis data. Structural response field simulation is performed based on environmental condition parameter analysis data to obtain parameter-correlated structural response field data. The cumulative damage of structural nodes is calculated by performing structural node damage accumulation calculation on the parameter-correlated structural response field data to obtain the cumulative node damage data; Based on the cumulative node damage data, the impact of the defect structure on the quantitative data is compensated for under different environmental conditions to obtain defect-environment structure impact compensation data.

[0010] Preferably, the defect evolution trend is estimated based on the defect-environment structure impact compensation data and the spatiotemporal trajectory data, including the following steps: Based on the defect-environment structure impact compensation data, the rate of change of defect state under different environmental conditions is extracted from the spatiotemporal change trajectory data of defect to obtain defect change rate data under different environmental conditions. Based on defect change rate data and defect-environment structure influence compensation data under different environmental conditions, multi-factor coupling effect decomposition is performed to obtain multi-factor coupling effect data. Effect time series matching is performed on multi-factor coupling effect data to obtain multi-factor effect time series matching data; Based on the multi-factor coupling effect data and the multi-factor effect time series matching data, the defect evolution trend is estimated from the spatiotemporal change trajectory data of the defect, and the defect evolution trend data is obtained.

[0011] Preferably, step S24 includes the following steps: Step S241: Based on the defect evolution clustering data, perform theoretical failure cycle analysis on the historical building structure defect identification data for different defect types to obtain defect theoretical failure cycle data; Step S242: Based on the defect evolution clustering data, perform risk accumulation periodic fluctuation analysis on the defect theoretical failure cycle data among different failure modes to obtain risk accumulation periodic fluctuation data; Step S243: Based on the defect spatial distribution density data, define the risk base increment between different defect types in the defect theoretical failure cycle data to obtain the risk base increment data between different defect types; Step S244: Conduct a risk level benchmark assessment based on the risk base increment data and risk accumulation cycle fluctuation data between different defect types to obtain risk level benchmark data.

[0012] Preferably, step S3 includes the following steps: Step S31: Perform convolution calculation on the risk level baseline data to obtain the risk level baseline convolution data; Step S32: Obtain historical building environmental monitoring data, identify environmental impact factors based on the defect evolution trend data according to the historical building environmental monitoring data, and obtain environmental related impact factors; Step S33: Perform dynamic risk impact correction on the baseline convolutional data of risk level based on environmental correlation impact factors to obtain risk impact correction data.

[0013] Preferably, step S32 includes the following steps: Step S321: Perform stratified analysis of environmental parameters on the environmental monitoring data of historical buildings to obtain stratified distribution data of environmental parameters; Step S322: Based on the hierarchical distribution data of environmental parameters, perform an environmental-driven degradation assessment on the defect evolution trend data to obtain environmental-driven degradation data; Step S323: Perform degradation response function fitting on the environment-driven degradation data to obtain the degradation response function; Step S324: Identify environmental impact factors in the environmental-driven degradation data based on the degradation response function to obtain environmentally related impact factors.

[0014] Secondly, this application provides a dynamic risk assessment system for historical buildings, including: The data acquisition module is used to collect historical building structure data through monitoring equipment, obtain historical building structure monitoring data, perform intelligent identification and analysis of structural defects on historical building structure monitoring data, obtain historical building structure defect identification data, and perform spatial distribution density analysis between defects based on historical building structure defect identification data to obtain defect spatial distribution density data. The analysis module is used to mark the spatiotemporal change trajectory of defects based on the spatial distribution density data of defects, to obtain the spatiotemporal change trajectory data of defects, to estimate the evolution trend of defects based on the spatiotemporal change trajectory data of defects, to obtain the evolution trend data of defects, and to conduct a risk level benchmark assessment of historical buildings based on the evolution trend data of defects, to obtain the risk level benchmark data. The correction module is used to acquire historical building environmental monitoring data, identify environmental impact factors based on the historical building environmental monitoring data to identify defect evolution trend data, obtain environmentally related impact factors, and dynamically correct the risk level benchmark data based on the environmentally related impact factors to obtain risk impact correction data. The assessment module is used to construct a dynamic risk assessment model for historical buildings by using adaptive learning algorithms to correct risk impact data. The dynamic risk assessment model for historical buildings is then deployed on a cloud monitoring platform to perform dynamic risk assessment and early warning for historical buildings.

[0015] In summary, this application includes the following beneficial technical effects: This application provides a dynamic risk assessment method for historical buildings. Through multi-source monitoring equipment and data fusion technology, it achieves comprehensive and continuous data collection on the apparent state and internal responses of historical buildings, overcoming the limitations of traditional manual inspections in terms of their partiality and periodicity. This provides a high-precision and timely data foundation for risk assessment. By introducing defect spatiotemporal trajectory marking and evolution trend estimation, discrete defect information is transformed into a continuous dynamic evolution model, achieving a leap from static assessment to dynamic prediction. This method can accurately capture the expansion patterns and rates of defects, greatly improving the foresight and accuracy of risk warnings. By identifying environmentally related influencing factors and dynamically correcting risk impacts, it profoundly reveals the dynamic coupling mechanism between environmental elements such as temperature, humidity, and wind force and structural degradation. This allows the risk assessment results to respond to environmental changes in real time, significantly enhancing the scientific nature and environmental adaptability of the assessment model. A dynamic risk assessment model is constructed based on an adaptive learning algorithm and deployed on a cloud platform, thus maintaining high accuracy and reliability of the assessment over the long term. Simultaneously, it realizes the intelligentization and automation of the assessment process, greatly improving the efficiency and effectiveness of historical building protection management and providing strong decision support for implementing precise preventative protection strategies. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a flowchart of the method for dynamic risk assessment of historical buildings in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of a system for dynamic risk assessment of historical buildings according to an embodiment of this application. Detailed Implementation

[0019] The following is in conjunction with the appendix Figure 1-2 This application will be described in further detail.

[0020] Example 1 This application discloses a method for dynamic risk assessment of historical buildings.

[0021] Reference Figure 1 A dynamic risk assessment method for historical buildings includes the following steps: Step S1: Collect historical building structure data through monitoring equipment to obtain historical building structure monitoring data; perform intelligent identification and analysis of structural defects on the historical building structure monitoring data to obtain historical building structure defect identification data; and perform spatial distribution density analysis between defects based on the historical building structure defect identification data to obtain defect spatial distribution density data. Step S2: Mark the spatiotemporal change trajectory of defects based on the spatial distribution density data of defects to obtain spatiotemporal change trajectory data of defects. Estimate the evolution trend of defects based on the spatiotemporal change trajectory data of defects to obtain evolution trend data of defects. Conduct a risk level benchmark assessment of historical buildings based on the evolution trend data of defects to obtain risk level benchmark data of risks. Step S3: Obtain historical building environmental monitoring data, identify environmental impact factors based on the defect evolution trend data according to the historical building environmental monitoring data, obtain environmentally related impact factors, and dynamically correct the risk level benchmark data based on the environmentally related impact factors to obtain risk impact corrected data; Step S4: Construct a dynamic risk assessment model for the risk impact correction data using an adaptive learning algorithm to obtain a dynamic risk assessment model for historical buildings. Deploy the dynamic risk assessment model for historical buildings on a cloud monitoring platform to perform dynamic risk assessment and early warning for historical buildings.

[0022] Specifically, the process begins with collecting structural data from historical buildings using monitoring equipment. After acquiring this data, intelligent structural defect identification technology is applied to analyze and process it, extracting structural defect identification data. Based on this data, the spatial distribution density of various structural defects is calculated and analyzed to obtain defect spatial distribution density data. Next, using this spatial distribution density data as a basis, the spatiotemporal trajectories of each structural defect are marked, generating defect spatiotemporal trajectory data. Based on this trajectory data, a trend estimation algorithm is used to analyze the evolution direction and speed of the defects, obtaining defect evolution trend data. Finally, this defect evolution trend data is combined with the analysis of the historical building's structural defects. The risk level of the historical building is assessed to determine the baseline risk level data. Then, environmental monitoring data of the building's environment is collected. Based on this data, the portion of the defect evolution trend data affected by environmental factors is identified, and environmentally related influencing factors are selected. These factors are then used to dynamically adjust and correct the baseline risk level data, resulting in risk impact correction data. Finally, an adaptive learning algorithm is used to train and construct a model based on the risk impact correction data, forming a dynamic risk assessment model for the historical building. This model is deployed to a cloud monitoring platform, which uses the model in real-time to dynamically assess the structural status of the historical building and triggers an early warning mechanism when the risk exceeds a preset threshold.

[0023] By adopting the above technical solutions, the efficiency and accuracy of structural defect identification are improved through automated data acquisition and intelligent identification technologies. The combination of spatiotemporal change trajectories and environmental impact factors realizes the dynamism and comprehensiveness of risk assessment. The adaptive model can continuously optimize the assessment accuracy as data accumulates, and cloud deployment ensures the real-time nature of risk assessment and early warning. This provides scientific and efficient technical support for the preventive protection of historical buildings and effectively reduces the risk of damage to historical buildings caused by untimely or inaccurate risk assessment.

[0024] It should be noted that step S1 includes the following steps: Step S11: Collect historical building structure data through monitoring equipment to obtain historical building structure monitoring data; wherein, the monitoring equipment is deployed at key structural parts of the historical building; Step S12: Perform data preprocessing and fusion on the historical building structure monitoring data to obtain historical building structure fusion data; Step S13: Perform intelligent structural defect identification and analysis on the fused data of historical building structures to obtain structural defect identification data of historical buildings; Step S14: Perform spatial distribution density analysis between defects based on the historical building structural defect identification data to obtain defect spatial distribution density data.

[0025] Specifically, based on the structural characteristics and stress analysis results of historical buildings, monitoring equipment is deployed at key structural components, such as beam-column joints, load-bearing walls, and roof trusses—locations prone to structural damage. The monitoring equipment collects real-time structural data such as displacement, stress, and vibration frequency at these key components, thus obtaining historical building structural monitoring data. For the collected historical building structural monitoring data, preprocessing operations are first performed, including outlier removal, missing data filling, and data format standardization. Then, a data fusion algorithm is used to integrate the heterogeneous data collected by different types of monitoring equipment, eliminating data redundancy and conflicts, to obtain the final historical building structural monitoring data. Structural fusion data: Using intelligent structural defect recognition algorithms based on deep learning or machine vision, the structural fusion data of historical buildings is analyzed to identify structural defects such as cracks, corrosion, and deformation reflected in the data, generating historical building structural defect recognition data. The recognition process adjusts the recognition parameters based on the building type and structural characteristics of the historical building to improve the targeting of defect recognition. Based on the historical building structural defect recognition data, spatial density analysis methods are used to calculate parameters such as the number of various defects per unit area and the average distance between defects, and to analyze the degree of defect aggregation in different areas of the historical building, obtaining defect spatial distribution density data.

[0026] By employing the above technical solutions, the deployment of monitoring equipment at key structural locations avoids wasting monitoring resources and ensures that the collected data accurately reflects the core structural state of historical buildings. This effectively solves the problem of invalid data caused by the blind deployment of equipment in traditional monitoring. Data preprocessing and fusion operations eliminate interference factors and heterogeneity in the original monitoring data, providing a high-quality data foundation for subsequent defect identification and improving the accuracy of defect identification. Compared with manual identification, intelligent structural defect identification technology is more efficient and objective, reducing errors caused by subjective human judgment. Defect spatial distribution density analysis provides a key spatial dimension for subsequent defect spatiotemporal change trajectory marking and risk assessment, helping assessors accurately grasp the impact of the spatial aggregation characteristics of defects on building structural safety, and further improving the scientificity and reliability of the entire risk assessment method.

[0027] It should be noted that step S2 includes the following steps: Step S21: Mark the spatiotemporal change trajectory of defects in historical building structure monitoring data based on the spatial distribution density data of defects to obtain the spatiotemporal change trajectory data of defects; Step S22: Estimate the defect evolution trend based on the spatiotemporal change trajectory data of defects in historical building structures to obtain defect evolution trend data; Step S23: Perform trend clustering and consistency analysis on the defect evolution trend data to obtain defect evolution clustering data; Step S24: Based on the defect evolution clustering data and defect spatial distribution density data, conduct a risk level benchmark assessment on the historical building structural defect identification data to obtain risk level benchmark data.

[0028] Specifically, the first step involves using the spatial distribution density data of defects as a reference, combined with the collection results of historical building structure monitoring data at different time points, to mark the trajectory information such as the location and morphological changes of various structural defects. The spatial coordinates and state parameters of the defects at different time points are recorded, thus obtaining the spatiotemporal change trajectory data of the defects. During the marking process, data is recorded according to defect type to ensure the clarity of the trajectory data. The second step, based on the spatiotemporal change trajectory data of the defects, uses a trend estimation model to analyze the development direction, rate of change, and severity escalation trend of each defect in the historical building structure defect identification data. This predicts the evolution state of the defects in the future, obtaining defect evolution trend data. The trend estimation model is adjusted based on the historical change patterns of the defects. The parameters are as follows: The third step is to perform trend clustering analysis on the defect evolution trend data. Clustering algorithms are used to group defects with similar evolution trends into the same category. Simultaneously, the consistency of evolution within the same category is examined, and the synchronicity and difference in defect evolution within the category are analyzed to obtain defect evolution clustering data. A reasonable similarity threshold is set during the clustering process to ensure the rationality of the clustering results. The fourth step is to integrate the defect evolution clustering data with the defect spatial distribution density data, and refer to the historical building structural safety assessment standards to assess the impact of each defect in the historical building structural defect identification data on the overall structural safety of the building. Risk levels are classified to obtain risk level benchmark data. The assessment process considers the clustering effect and evolution risk of different categories of defects to ensure the comprehensiveness of the benchmark data.

[0029] By employing the aforementioned technical solutions, the dynamic development process of defects is clearly presented through the marking of their spatiotemporal changes, solving the problem of traditional assessments that only focus on the current state of defects while ignoring historical changes. Defect evolution trend estimation provides a forward-looking basis for risk warning, helping to identify potential risks in advance. Trend clustering and consistency analysis integrate scattered defect evolution information, avoiding the one-sidedness caused by isolated assessments of individual defects, and enabling a more accurate grasp of the evolutionary patterns of defect groups. Combining defect evolution clustering data with spatial distribution density data for risk level benchmark assessment fully considers the group effect and spatial characteristics of defects, making the benchmark assessment results more consistent with the actual structural safety status of historical buildings, laying a reliable foundation for subsequent dynamic corrections.

[0030] Furthermore, step S22 includes the following steps: Step S221: Extract the geometric features of each defect from the structural defect identification data of historical buildings to obtain defect geometric feature data; Step S222: Based on the defect geometric feature data, quantify the structural impact of each defect in the historical building structural defect identification data to obtain the defect structural impact quantification data; Step S223: Based on the spatiotemporal change trajectory data of defects, extract the environmental response of each defect from the historical building structure monitoring data to obtain defect environmental response data; Step S224: Based on the defect environmental response data, perform impact compensation on the defect structure impact quantification data under different environmental conditions to obtain defect-environment structure impact compensation data; Step S225: Estimate the defect evolution trend based on the defect-environment structure influence compensation data to obtain defect evolution trend data.

[0031] Specifically, the first step involves extracting geometric features from each defect recorded in the historical building structural defect identification data. Image analysis or 3D modeling techniques are used to obtain parameters such as the defect's length, width, depth, area, volume, and morphological characteristics, establishing a geometric feature profile for each defect, and obtaining defect geometric feature data. The feature extraction process adjusts the extraction parameters according to the defect type (e.g., cracks, corrosion, deformation) to ensure feature accuracy. The second step, based on the defect geometric feature data and the historical building's structural mechanics model, calculates the impact of each defect on the load-bearing capacity, stiffness, stability, and other mechanical properties of the structural components, quantifying the degree of damage to structural function, and obtaining quantitative data on the structural impact of defects. The quantitative calculation references relevant structural design codes to ensure the results are standardized. The third step, based on the spatiotemporal trajectory data of the defects, analyzes the defects in the historical building structural monitoring data under different environmental conditions (e.g., temperature changes, etc.). The first step involves analyzing the response characteristics of defects under varying humidity and wind conditions. This process extracts parameters showing the state changes of defects under environmental factors, yielding environmental response data. Response extraction is recorded separately for different environmental conditions to ensure data relevance. The second step analyzes the differences in the impact of different environmental conditions on the defect structure based on the environmental response data. This calculates the structural impact deviation caused by environmental factors and compensates for the quantitative data of the defect's structural impact, eliminating interference from different environmental conditions in the defect impact assessment. This results in defect-environmental structural impact compensation data. The compensation process establishes a correspondence between environmental parameters and impact deviations to ensure the accuracy of the compensation. The third step uses the defect-environmental structural impact compensation data as a foundation, combined with the historical change patterns of defects in the spatiotemporal trajectory data. Time series analysis or prediction models are then used to estimate the future evolution direction, rate of change, and severity escalation trend of each defect, yielding defect evolution trend data.

[0032] By employing the above technical solutions, geometric feature extraction provides accurate basic data for quantifying the impact of defects, shifting the assessment of the structural impact from qualitative to quantitative, thus improving the scientific rigor of the assessment. Quantifying the structural impact of defects clarifies the severity of each defect, providing a quantitative basis for subsequent risk assessment. Defect environmental response extraction and compensation operations resolve the bias problem in defect impact assessment under different environmental conditions, avoiding inaccurate evolution trend estimations due to environmental factors. Defect evolution trend estimation based on compensation data fully considers the geometric characteristics, structural impact, and environmental response of defects, making the trend estimation results more consistent with reality and enabling more accurate prediction of the future development of defects, providing precise technical support for risk early warning of historical buildings.

[0033] Furthermore, based on the environmental response data of the defects, the impact compensation for the quantitative data of the structural impact of the defects under different environmental conditions is performed, including the following steps: Based on the defective environmental response data, key parameters are analyzed under different environmental conditions to obtain environmental condition parameter analysis data. Structural response field simulation is performed based on environmental condition parameter analysis data to obtain parameter-correlated structural response field data. The cumulative damage of structural nodes is calculated by performing structural node damage accumulation calculation on the parameter-correlated structural response field data to obtain the cumulative node damage data; Based on the cumulative node damage data, the impact of the defect structure on the quantitative data is compensated for under different environmental conditions to obtain defect-environment structure impact compensation data.

[0034] Specifically, firstly, an in-depth analysis of the defect environmental response data is conducted, dissecting key environmental parameters affecting defect state changes under different environmental conditions (such as high temperature, high humidity, strong wind, rain, and snow), including temperature, humidity, wind speed, and precipitation. This clarifies the value range and variation patterns of each key parameter under different environmental conditions, yielding environmental condition parameter analysis data. The analysis process involves classifying and statistically analyzing environmental parameters to ensure comprehensiveness. Next, based on the environmental condition parameter analysis data, a structural response field model of the historical building is constructed. Using key environmental parameters as input variables, the model simulates the stress distribution, displacement distribution, and vibration response of the historical building structure under different combinations of environmental parameters, reconstructing the actual stress and deformation state of the structure under different environmental conditions. This yields parameter-correlated structural response field data. The simulation process will... The model's accuracy is ensured by referencing the actual structural parameters of historical buildings. Then, structural node damage accumulation is calculated using parameter-correlated structural response field data. Based on the structure's response state under different environmental conditions, damage accumulation theory is employed to calculate the cumulative damage of each structural node under long-term environmental influences. The correlation between damage accumulation and changes in environmental parameters is analyzed to obtain node damage accumulation data. The calculation process considers the superposition effect of damage to ensure the accuracy of the accumulation. Finally, based on the node damage accumulation data, the degree of interference of node damage accumulation on the defective structure under different environmental conditions is analyzed. Influence compensation coefficients are calculated for each environmental condition, and these compensation coefficients are used to adjust the quantitative data of the defective structure's influence, eliminating the structural influence assessment bias caused by different environmental conditions, thus obtaining defect-environment structural influence compensation data.

[0035] By employing the above technical solutions, the core environmental factors affecting the defective structure were accurately identified through the analysis of key environmental parameters, avoiding ineffective analysis of irrelevant environmental parameters. Structural response field simulation can realistically reproduce the structural state of historical buildings under different environments, providing a reliable basis for damage accumulation calculation. The nodal damage accumulation calculation fully considers the long-term impact of environmental factors on the structure, reflecting the time-cumulative effect of damage. Based on the impact compensation of damage accumulation data, the interference of different environmental conditions on the quantitative impact of defective structures can be accurately eliminated, making the compensated data more consistent with the actual impact of defects on the structure. This provides accurate data support for subsequent defect evolution trend estimation, effectively improving the accuracy and reliability of the entire risk assessment method.

[0036] Furthermore, based on the defect-environmental structure impact compensation data, the defect evolution trend is estimated from the spatiotemporal trajectory data, including the following steps: Based on the defect-environment structure impact compensation data, the rate of change of defect state under different environmental conditions is extracted from the spatiotemporal change trajectory data of defect to obtain defect change rate data under different environmental conditions. Based on defect change rate data and defect-environment structure influence compensation data under different environmental conditions, multi-factor coupling effect decomposition is performed to obtain multi-factor coupling effect data. Effect time series matching is performed on multi-factor coupling effect data to obtain multi-factor effect time series matching data; Based on the multi-factor coupling effect data and the multi-factor effect time series matching data, the defect evolution trend is estimated from the spatiotemporal change trajectory data of the defect, and the defect evolution trend data is obtained.

[0037] Specifically, firstly, based on the defect-environment structural impact compensation data, and combined with the state parameters of the defect at different time points and under different environmental conditions in the defect spatiotemporal trajectory data, the rate of state change of each defect under different environmental conditions (such as high temperature, high humidity, normal temperature and humidity, etc.) is calculated, including the rate of defect length growth, the rate of width expansion, and the rate of depth deepening. The average value, maximum value, and variation law of the rate under different environmental conditions are statistically analyzed to obtain the defect change rate data under different environmental conditions. The rate extraction is calculated segment by segment according to the time series to ensure the continuity of the data. Next, based on the defect change rate data under different environmental conditions and the defect-environment structural impact compensation data, the interaction relationship between multiple factors affecting defect evolution (such as environmental factors, structural stress factors, and defect-specific characteristics) is analyzed. A coupling effect decomposition algorithm is used to decompose the evolution effect generated by the combined action of multiple factors into the independent effects of each individual factor and the interaction between factors. The decomposition process obtains multi-factor coupled effect data, setting reasonable effect separation thresholds to ensure the accuracy of the decomposition results. Then, it performs temporal matching of the multi-factor coupled effect data, correlating the effects of different factors with time nodes in the defect spatiotemporal trajectory data based on the order and duration of each factor's effect over time. This establishes a correlation between effects and time, analyzing the superposition and staggering patterns of different factor effects over time to obtain multi-factor effect temporal matching data. The temporal matching references historical defect change time points to ensure matching accuracy. Finally, it integrates the multi-factor coupled effect data and the multi-factor effect temporal matching data, combined with the historical evolution patterns of defects in the defect spatiotemporal trajectory data, and uses a prediction algorithm to estimate the future evolution direction, rate of change, and severity escalation points of defects. The prediction process adjusts the prediction model parameters according to the effect weights of different factors, ultimately obtaining defect evolution trend data.

[0038] By employing the above technical solutions, the impact of environmental factors on the evolution speed of defects is clearly understood through the extraction of defect change rates under different environmental conditions, providing a rate basis for trend estimation. Multi-factor coupling effect decomposition solves the problem of complex and difficult-to-distinguish evolutionary effects caused by the interaction of multiple factors, accurately identifying the independent contribution and interactive influence of each factor on defect evolution. Effect time-series matching links factor effects with the time dimension, avoiding trend estimation bias caused by ignoring the timing of effect occurrence. Evolutionary trend estimation based on multi-factor coupling effects and time-series matching fully considers the role and time patterns of various influencing factors, making the trend prediction results more consistent with the actual evolution process of defects, effectively improving the accuracy and reliability of defect evolution trend estimation, and providing a precise and forward-looking basis for the benchmark assessment of historical building risk levels.

[0039] Furthermore, step S24 includes the following steps: Step S241: Based on the defect evolution clustering data, perform theoretical failure cycle analysis on the historical building structure defect identification data for different defect types to obtain defect theoretical failure cycle data; Step S242: Based on the defect evolution clustering data, perform risk accumulation periodic fluctuation analysis on the defect theoretical failure cycle data among different failure modes to obtain risk accumulation periodic fluctuation data; Step S243: Based on the defect spatial distribution density data, define the risk base increment between different defect types in the defect theoretical failure cycle data to obtain the risk base increment data between different defect types; Step S244: Conduct a risk level benchmark assessment based on the risk base increment data and risk accumulation cycle fluctuation data between different defect types to obtain risk level benchmark data.

[0040] Specifically, the first step involves analyzing the theoretical time period required for each type of defect to pose a serious threat to structural safety from its appearance, based on the defect evolution clustering data and the different defect types (such as cracks, corrosion, and deformation) identified in the clustering results. This analysis considers the structural material characteristics of historical buildings, structural design standards, and defect failure cases of similar buildings. The theoretical failure duration and key node state parameters during the failure process are calculated for each type of defect, yielding theoretical failure cycle data. The cycle analysis adjusts the calculation results based on the initial severity of the defect to ensure the relevance of the cycle data. The second step, based on the defect evolution clustering data, analyzes the risk accumulation pattern of the same type of defect within the theoretical failure cycle. This involves considering the structural stress changes of historical buildings under different seasons and environmental cycles (such as rainy season and typhoon season) to study the fluctuation characteristics of defect risk accumulation over time. Parameters such as the peak time, fluctuation amplitude, and cycle length of risk accumulation are calculated to obtain risk accumulation cycle fluctuation data. The fluctuation analysis references long-term monitoring of risk changes. The process involves four steps: First, recording and ensuring the accuracy of fluctuation data. Second, analyzing the impact of various defects on structural safety in different density areas based on defect spatial distribution density data. This includes calculating the risk base difference between high-density and low-density areas for the same type of defect, defining the incremental risk base value, calculation basis, and contribution ratio of the incremental value to the overall risk for different defect types under different density conditions, and obtaining incremental risk base data for different defect types. The incremental definition is combined with structural mechanics analysis results to ensure the rationality of the incremental data. Third, integrating the incremental risk base data and risk accumulation cycle fluctuation data for different defect types, and referring to the historical building structural safety risk level classification standards, the incremental and fluctuation data are substituted into the risk assessment formula to calculate the current overall risk value of the historical building. Based on the risk value, risk levels are classified (e.g., low risk, medium risk, high risk, extremely high risk), obtaining risk level benchmark data. The assessment process involves weighted summation of the risks of different defect categories to ensure the comprehensiveness of the benchmark data.

[0041] By adopting the above technical solutions and using defect theory failure cycle analysis, key time-dimensional evidence is provided for risk assessment, enabling early prediction of defect risk outbreak time. Risk accumulation cycle fluctuation analysis considers the periodic change characteristics of risk, avoiding static risk assessment and making the assessment results more consistent with the actual change patterns of historical building risks. The definition of risk base increment fully considers the impact of defect spatial distribution density, solving the problem of underestimation or overestimation of risk caused by neglecting the defect clustering effect in traditional assessments. The risk level benchmark assessment combining incremental and fluctuation data comprehensively considers risk from multiple dimensions such as time, space, and defect type, making the benchmark assessment results more comprehensive and accurate. This provides a scientific and reliable basis for subsequent dynamic correction of environmental impacts and effectively improves the rationality of historical building risk assessment.

[0042] It should be noted that step S3 includes the following steps: Step S31: Perform convolution calculation on the risk level baseline data to obtain the risk level baseline convolution data; Step S32: Obtain historical building environmental monitoring data, identify environmental impact factors based on the defect evolution trend data according to the historical building environmental monitoring data, and obtain environmental related impact factors; Step S33: Perform dynamic risk impact correction on the baseline convolutional data of risk level based on environmental correlation impact factors to obtain risk impact correction data.

[0043] Specifically, the first step involves convolutional calculations on the risk level baseline data. A suitable convolutional kernel (such as a Gaussian kernel) is used to smooth the baseline data, eliminating noise interference, enhancing risk characteristic information, and highlighting the differences between different risk levels. Simultaneously, the data dimensions are adjusted to better suit subsequent dynamic correction processing, resulting in risk level baseline convolutional data. The convolutional calculation adjusts the kernel parameters based on the distribution characteristics of the baseline data to ensure the validity of the convolutional results. The second step involves collecting environmental data such as temperature, humidity, wind speed, precipitation, and air quality (e.g., sulfur dioxide concentration, particulate matter concentration) from environmental monitoring equipment deployed around and inside the historical buildings. This yields historical building environmental monitoring data. A reasonable sampling frequency is set during the data collection process to ensure the real-time nature and continuity of the data. Based on this… Environmental monitoring data, combined with the correlation between defect status and environmental parameters in defect evolution trend data, is used to screen out environmental factors that significantly affect defect evolution trends using factor identification algorithms (such as principal component analysis and grey relational analysis). The influence range of each influencing factor is determined, resulting in environmentally related influencing factors. Factor identification results are verified through significance tests to ensure the reliability of the factors. In the third step, based on the environmentally related influencing factors, the influence of the current value status of each factor on the evolution of historical building structural defects is analyzed. The risk level correction coefficient caused by each factor is calculated, and the correction coefficient is substituted into the risk level benchmark convolutional data. The benchmark convolutional data is dynamically adjusted to correct the risk deviation caused by changes in current environmental conditions, resulting in risk impact correction data. The correction process sets different correction priorities according to the factor weights to ensure the rationality of the correction results.

[0044] By employing the above technical solution, convolution calculations on the risk level benchmark data effectively eliminate interference information in the benchmark data, improving data quality and stability, and providing a more reliable foundation for subsequent dynamic correction. The collection of historical building environmental monitoring data and the identification of environmentally related influencing factors accurately pinpoint the key factors affecting the evolution of defects and risk levels in the current environment, solving the problem of risk assessment lag caused by neglecting real-time environmental changes in traditional assessments. Based on the dynamic correction of environmentally related influencing factors, the risk assessment results can be adjusted in real time to follow changes in environmental conditions, ensuring the dynamism and timeliness of risk assessment, avoiding misjudgments of risk due to sudden changes in environmental factors, and further improving the accuracy and practicality of dynamic risk assessment for historical buildings.

[0045] Furthermore, step S32 includes the following steps: Step S321: Perform stratified analysis of environmental parameters on the environmental monitoring data of historical buildings to obtain stratified distribution data of environmental parameters; Step S322: Based on the hierarchical distribution data of environmental parameters, perform an environmental-driven degradation assessment on the defect evolution trend data to obtain environmental-driven degradation data; Step S323: Perform degradation response function fitting on the environment-driven degradation data to obtain the degradation response function; Step S324: Identify environmental impact factors in the environmental-driven degradation data based on the degradation response function to obtain environmentally related impact factors.

[0046] Specifically, the first step involves a stratified analysis of environmental parameters in the historical building environmental monitoring data. The data is divided into different levels based on parameter type (e.g., meteorological parameters, air quality parameters, soil moisture parameters). Each level is further subdivided according to the parameter's influence range (e.g., global environmental parameters, local regional parameters). Simultaneously, statistical analysis is performed on the value range, frequency of change, and fluctuation amplitude of parameters at each level. This establishes a hierarchical structure and characteristic profile of environmental parameters, resulting in stratified distribution data. The stratification process references the influence mechanism of environmental parameters on the historical building structure to ensure the rationality of the stratification results. The second step, based on the stratified distribution data of environmental parameters and the changes in the evolutionary state of defects in the defect evolution trend data, analyzes the driving effect of different levels of environmental parameters on defect degradation. It calculates indicators such as the rate of defect degradation and the increment of degradation degree caused by each level of parameter, assessing the driving contribution of different environmental parameters to defect evolution, and obtaining environmentally driven degradation data. The driving assessment will employ control... The first step involves analyzing the driving effect of a single parameter using the variable control method to ensure the accuracy of the assessment results. The second step involves fitting a degradation response function to the environmentally driven degradation data. Using environmental parameters as independent variables and the degree of defect degradation as the dependent variable, a curve fitting algorithm (such as linear regression, nonlinear regression, or machine learning fitting model) is employed to construct a quantitative relationship function between the environmental parameters and the degree of defect degradation. The function parameters are adjusted to minimize the error between the fitting result and the actual degradation data, resulting in the degradation response function. Cross-validation is used during the fitting process to verify the function's fitting accuracy and ensure its reliability. The third step involves analyzing the coefficients, significance levels, and sensitivity of each environmental parameter to the dependent variable (degree of defect degradation) based on the degradation response function. Environmental parameters with significant impacts on defect degradation are selected, and their influence weights and thresholds are determined. These parameters are defined as environmentally related influencing factors. Statistical tests are used to exclude parameters with insignificant influences to ensure the effectiveness of the factors.

[0047] By employing the above technical solutions, a hierarchical analysis of environmental parameters systematically organizes complex environmental monitoring data, solving the analytical difficulties caused by the disorganization of environmental parameters and making parameters of different types and impact ranges clearly identifiable. Environmentally driven degradation assessment clarifies the actual driving role of each environmental parameter in defect degradation, avoiding ineffective analysis of irrelevant environmental parameters. Degradation response function fitting establishes a quantitative relationship between environmental parameters and defect degradation, shifting the impact of environmental factors on defects from qualitative description to quantitative calculation, thus improving the scientific rigor of factor identification. Based on the identification of environmentally related influencing factors using response functions, the key environmental factors that truly affect defect evolution can be accurately screened, eliminating interfering factors and ensuring the targetedness and accuracy of subsequent dynamic correction of risk impacts, further enhancing the rigor and reliability of the dynamic risk assessment method for historical buildings.

[0048] Example 2 This application also discloses a dynamic risk assessment system for historical buildings.

[0049] Reference Figure 2 A dynamic risk assessment system for historical buildings, comprising: The data acquisition module is used to collect historical building structure data through monitoring equipment, obtain historical building structure monitoring data, perform intelligent identification and analysis of structural defects on historical building structure monitoring data, obtain historical building structure defect identification data, and perform spatial distribution density analysis between defects based on historical building structure defect identification data to obtain defect spatial distribution density data. The analysis module is used to mark the spatiotemporal change trajectory of defects based on the spatial distribution density data of defects, to obtain the spatiotemporal change trajectory data of defects, to estimate the evolution trend of defects based on the spatiotemporal change trajectory data of defects, to obtain the evolution trend data of defects, and to conduct a risk level benchmark assessment of historical buildings based on the evolution trend data of defects, to obtain the risk level benchmark data. The correction module is used to acquire historical building environmental monitoring data, identify environmental impact factors based on the historical building environmental monitoring data to identify defect evolution trend data, obtain environmentally related impact factors, and dynamically correct the risk level benchmark data based on the environmentally related impact factors to obtain risk impact correction data. The assessment module is used to construct a dynamic risk assessment model for historical buildings by using adaptive learning algorithms to correct risk impact data. The dynamic risk assessment model for historical buildings is then deployed on a cloud monitoring platform to perform dynamic risk assessment and early warning for historical buildings.

[0050] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention, they should all fall within the protection scope of the present invention.

[0051] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0052] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method of dynamic risk assessment of historic buildings, characterized in that, The method comprises the following steps: Step S1: collecting historical building structure data by a monitoring device to obtain historical building structure monitoring data, performing intelligent identification analysis on the historical building structure monitoring data to obtain historical building structure defect identification data, performing spatial distribution density analysis on the historical building structure defect identification data to obtain defect spatial distribution density data, and performing time-space change trajectory marking on the defect spatial distribution density data to obtain defect time-space change trajectory data; Step S2: performing defect evolution trend estimation based on the defect time-space change trajectory data to obtain defect evolution trend data, performing historical building risk level benchmark evaluation based on the defect evolution trend data to obtain risk level benchmark data, and performing environmental impact factor identification on the defect evolution trend data based on historical building environment monitoring data to obtain environmental correlation impact factors; Step S3: performing risk influence dynamic correction on the risk level benchmark data based on the environmental correlation impact factors to obtain risk influence correction data, and performing dynamic risk assessment model construction on the risk influence correction data by a self-adaptive learning algorithm to obtain a historical building dynamic risk assessment model; The step S1 comprises the following steps:

2. The method of claim 1, wherein, Step S11: collecting historical building structure data by a monitoring device to obtain historical building structure monitoring data; wherein the monitoring device is deployed at a key structure part of the historical building; Step S12: performing data preprocessing and fusion on the historical building structure monitoring data to obtain historical building structure fusion data; Step S13: performing intelligent identification analysis on the historical building structure fusion data to obtain historical building structure defect identification data; Step S14: performing spatial distribution density analysis on the historical building structure defect identification data based on the historical building structure defect identification data to obtain defect spatial distribution density data. The step S2 comprises the following steps:

3. A method of dynamic risk assessment of historic buildings according to claim 2, characterized in that, Step S21: performing time-space change trajectory marking on the historical building structure monitoring data based on the defect spatial distribution density data to obtain defect time-space change trajectory data; Step S22: performing defect evolution trend estimation on the historical building structure defect identification data based on the defect time-space change trajectory data to obtain defect evolution trend data; Step S23: performing trend clustering and consistency analysis on the defect evolution trend data to obtain defect evolution clustering data; Step S24: performing risk level benchmark evaluation on the historical building structure defect identification data based on the defect evolution clustering data and the defect spatial distribution density data to obtain risk level benchmark data. The step S22 comprises the following steps:

4. The method of claim 3, wherein, Step S221: performing geometric feature extraction on each defect of the historical building structure defect identification data to obtain defect geometric feature data; Step S222: performing structure influence quantification on each defect of the historical building structure defect identification data based on the defect geometric feature data to obtain defect structure influence quantification data; and Step S223: performing trend clustering and consistency analysis on the defect structure influence quantification data to obtain defect evolution clustering data. Step S223: Extracting the environmental response data of each defect based on the defect spatiotemporal trajectory data and the historical building structure monitoring data, to obtain the defect environmental response data; Step S224: Compensating the influence of different environmental conditions on the defect structure quantitative data according to the defect environmental response data, to obtain the defect-environmental structure influence compensation data; Step S225: Estimating the defect evolution trend data based on the defect-environmental structure influence compensation data and the defect spatiotemporal trajectory data.

5. A method of dynamic risk assessment of historic buildings according to claim 4, characterized in that, The step S224 includes the following steps: According to the defect environmental response data, the key parameter analysis between different environmental conditions is performed to obtain the environmental condition parameter analysis data; Based on the environmental condition parameter analysis data, the structure response field simulation is performed to obtain the parameter associated structure response field data; The structure node damage accumulation calculation is performed on the parameter associated structure response field data to obtain the node damage accumulation data; According to the node damage accumulation data, the influence compensation between different environmental conditions on the defect structure quantitative data is performed to obtain the defect-environmental structure influence compensation data.

6. The method of dynamic risk assessment of historic buildings according to claim 4, characterized in that, The step S225 includes the following steps: According to the defect-environmental structure influence compensation data, the change rate data between different defect states under different environmental conditions is extracted from the defect spatiotemporal trajectory data, to obtain the defect change rate data under different environmental conditions; Based on the defect change rate data under different environmental conditions and the defect-environmental structure influence compensation data, the multi-factor coupling effect data is obtained by decomposing the multi-factor coupling effect; The effect time sequence matching data is obtained by performing effect time sequence matching on the multi-factor coupling effect data; According to the multi-factor coupling effect data and the multi-factor effect time sequence matching data, the defect evolution trend data is estimated based on the defect spatiotemporal trajectory data, to obtain the defect evolution trend data.

7. The method of claim 3, wherein, The step S24 includes the following steps: Step S241: According to the defect evolution clustering data, the theoretical failure period analysis between different defect types is performed on the historical building structure defect identification data to obtain the defect theoretical failure period data; Step S242: Based on the defect evolution clustering data, the risk accumulation periodic fluctuation analysis between different failure modes is performed on the defect theoretical failure period data to obtain the risk accumulation periodic fluctuation data; Step S243: According to the defect spatial distribution density data, the risk base increment data between different defect types is defined by performing the risk base increment analysis between different defect types on the defect theoretical failure period data; Step S244: According to the risk base increment data between different defect types and the risk accumulation periodic fluctuation data, the risk level benchmark data is obtained by performing the risk level benchmark evaluation.

8. The method of dynamic risk assessment of historic buildings according to claim 1, characterized in that, The step S3 includes the following steps: Step S31: Convolution calculation is performed on the risk level benchmark data to obtain the risk level benchmark convolution data; Step S32: acquire historical building environment monitoring data, identify environmental impact factors from the defect evolution trend data based on the historical building environment monitoring data, and obtain environmental correlation impact factors; Step S33: based on the environmental correlation impact factors, perform dynamic risk impact correction on the risk level benchmark convolution data to obtain risk impact correction data.

9. A method of dynamic risk assessment of a historic building according to claim 8, wherein, The step S32 includes the following steps: Step S321: perform environmental parameter hierarchical analysis on the historical building environment monitoring data to obtain environmental parameter hierarchical distribution data; Step S322: perform environment-driven degradation evaluation on the defect evolution trend data based on the environmental parameter hierarchical distribution data to obtain environment-driven degradation data; Step S323: perform degradation response function fitting processing on the environment-driven degradation data to obtain a degradation response function; Step S324: identify environmental impact factors from the environment-driven degradation data based on the degradation response function to obtain environmental correlation impact factors.

10. A system for dynamic risk assessment of historic buildings, applied to a method for dynamic risk assessment of historic buildings according to any one of claims 1 to 9, characterized in that, Comprise: The data acquisition module is used for collecting historical building structure data through the monitoring equipment to obtain historical building structure monitoring data, performing intelligent recognition and analysis on the historical building structure monitoring data to obtain historical building structure defect recognition data, analyzing the spatial distribution density of defects based on the historical building structure defect recognition data, and obtaining defect spatial distribution density data; The analysis module is used for marking the defect space-time change trajectory based on the defect space-time change trajectory data to obtain defect space-time change trajectory data, estimating the defect evolution trend based on the defect space-time change trajectory data to obtain defect evolution trend data, and evaluating the historical building risk level benchmark based on the defect evolution trend data to obtain risk level benchmark data; The correction module is used for acquiring historical building environment monitoring data, identifying environmental impact factors from the defect evolution trend data based on the historical building environment monitoring data, and obtaining environmental correlation impact factors, and performing dynamic risk impact correction on the risk level benchmark data based on the environmental correlation impact factors to obtain risk impact correction data; The evaluation module is used for constructing a dynamic risk evaluation model based on the risk impact correction data through an adaptive learning algorithm to obtain a historical building dynamic risk evaluation model, and deploying the historical building dynamic risk evaluation model on a cloud monitoring platform to perform historical building dynamic risk evaluation and early warning.

Images