Building external envelope structure safety risk prevention and control method, system, equipment and medium

Abstract

The invention relates to a safety risk prevention and control method, system and device for an external envelope structure of a building and a medium. The method comprises the steps of obtaining three-dimensional scanning data of the building and generating a three-dimensional structure model of the building; structural features of the building are extracted from the three-dimensional structural model, a corresponding environment monitoring scheme is generated in combination with a clustering analysis algorithm, and the collection position and the data type of real-time environment data are determined; collecting real-time environment data of the external envelope structure, and dynamically filtering the real-time environment data based on an adaptive filtering algorithm to obtain standard environment data; analyzing the standard environment data by using a support vector machine algorithm, and triggering a safety early warning message under the condition that a sudden structure safety risk is identified; and obtaining structure multi-source data, predicting the structure multi-source data by using a preset safety prediction model to obtain a safety risk development trend of the building structure, and estimating a potential risk based on the safety risk development trend. The method has the effect of improving the safety of the external maintenance structure of the building.

Description

Technical Field

[0001] The present application relates to the technical field of building structure safety monitoring, and in particular, to a method, system, device and medium for preventing and controlling safety risks of building envelopes. Background Art

[0002] Currently, with the increase in high-rise buildings and large public facilities, the safety of building envelopes has gradually attracted attention. The safety monitoring of building envelopes mainly relies on manual inspections or simple sensor deployments. By regularly collecting data such as temperature, humidity, and stress to identify potential risks. However, in the face of dynamic environmental changes and emergencies, the monitoring scheme with a fixed sampling frequency in this traditional monitoring method cannot quickly capture key data, and there are often problems of insufficient real-time performance and limited coverage, making it difficult to respond promptly to risk changes in complex environments.

[0003] The above-mentioned existing technical solutions have the following defects: The existing safety monitoring methods for building envelopes have poor real-time performance and insufficient flexibility, and cannot effectively cope with the dynamic risks of complex building structures. Therefore, there is room for improvement. Summary of the Invention

[0004] In order to improve the safety of building envelopes, the present application provides a method, system, device and medium for preventing and controlling safety risks of building envelopes.

[0005] The first invention object of the present application is achieved through the following technical solutions: A method for preventing and controlling safety risks of building envelopes, the method for preventing and controlling safety risks of building envelopes includes: Obtain three-dimensional scan data of a building, and generate a three-dimensional structure model of the building based on the three-dimensional scan data through image recognition and three-dimensional modeling techniques; Extract the structural features of the building from the three-dimensional structure model, and based on the structural features, generate a corresponding environmental monitoring plan in combination with a clustering analysis algorithm, and determine the acquisition positions and data types of real-time environmental data; Collect the real-time environmental data of the envelope structure, and dynamically filter the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; Analyze the standard environmental data using a support vector machine algorithm, and trigger a safety warning message when a sudden structural safety risk is identified; Obtain multi-source structural data, use a preset safety prediction model to predict the multi-source structural data, obtain the development trend of the safety risk of the building structure, and estimate potential risks based on the development trend of the safety risk.

[0006] By adopting the above technical solutions, by obtaining the three-dimensional scanning data of the building and generating a three-dimensional structural model of the building through image recognition and three-dimensional modeling technologies, the overall structural model of the building can be quickly constructed, ensuring comprehensive analysis of each part of the building, thereby improving the accuracy of data collection; by extracting the structural features of the building from the three-dimensional structural model, based on the structural features, and generating an environmental monitoring plan in combination with the clustering analysis algorithm, a monitoring plan suitable for different parts of the building can be automatically generated, reducing the errors caused by human intervention, thereby improving the accuracy and flexibility of monitoring; by collecting the real-time environmental data of the envelope structure and dynamically filtering the real-time environmental data based on the adaptive filtering algorithm to obtain standard environmental data, the noise interference can be effectively filtered, improving the data quality, thereby ensuring the reliability of subsequent analysis; by using the support vector machine algorithm to analyze the standard environmental data and triggering a safety warning message when a sudden structural safety risk is identified, the sudden risk can be timely identified and feedback, ensuring the real-time nature of risk control, thereby reducing the impact of potential safety hazards.

[0007] In one example, the present application can be further configured as follows: extracting the structural features of the building from the three-dimensional structural model, and generating an environmental monitoring plan based on the structural features and in combination with the clustering analysis algorithm, specifically including: Performing geometric analysis based on the three-dimensional structural model, extracting the geometric parameters of the load-bearing structure, exterior wall, and key nodes of the building, and performing feature comparison and analysis on the geometric parameters in combination with the historical building structure database to identify the structural features; By performing clustering analysis on the structural features of different parts of the building, determining the key monitoring areas, and dynamically setting the sensor sampling frequency and monitoring data type for different key monitoring areas.

[0008] By adopting the above technical solutions, by performing geometric analysis based on the three-dimensional structural model, extracting the geometric parameters of the load-bearing structure, exterior wall, and key nodes of the building, and performing feature comparison and analysis on the geometric parameters in combination with the historical building structure database to identify the structural features, the key features of the building structure can be deeply analyzed, providing basic data for subsequent monitoring, thereby improving the pertinence and accuracy of the building monitoring plan; by performing clustering analysis on the structural features of different parts of the building, determining the key monitoring areas, and dynamically setting the sensor sampling frequency and monitoring data type for different key monitoring areas, the monitoring plan can be dynamically adjusted according to the characteristics of each part of the building, optimizing resource allocation, thereby improving the effectiveness of key area monitoring.

[0009] In one example, the present application can be further configured as follows: the clustering analysis of the structural features of different parts of the building specifically includes: Obtain the property parameters of building materials, and determine the high thermal expansion coefficient region and the stress concentration region according to the property parameters; Determine the thermal expansion region and / or crack propagation region through thermodynamic analysis and stress analysis, calculate the risk coefficient of each region, and determine the priority monitoring region based on the risk coefficient.

[0010] By adopting the above technical solution, by obtaining the property parameters of building materials and determining the high thermal expansion coefficient region and the stress concentration region according to the property parameters, it is possible to distinguish the important regions of the building structure according to different material characteristics, ensure the accuracy of the monitoring plan, and thus effectively improve the monitoring effect on the key regions; by determining the thermal expansion region and / or crack propagation region through thermodynamic analysis and stress analysis, calculating the risk coefficient of each region, and determining the priority monitoring region based on the risk coefficient, it is possible to give priority to monitoring the high-risk regions, reduce resource waste, and thus ensure the reliability and timeliness of risk detection.

[0011] In one example, the present application can be further configured as: collecting the real-time environmental data of the peripheral enclosure structure, and dynamically filtering the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data, specifically including: Dynamically adjust the filtering parameters according to the change situation of the real-time environmental data, and eliminate the invalid data affected by external interference; Perform noise suppression and signal enhancement through the adaptive filtering algorithm to obtain the standard environmental data.

[0012] By adopting the above technical solution, by collecting the real-time environmental data of the peripheral enclosure structure and dynamically filtering the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data, it is possible to adjust the filtering parameters in real time according to environmental changes, eliminate invalid data, ensure the purity of the data, and thus provide a stable data source for subsequent analysis; by performing noise suppression and signal enhancement through the adaptive filtering algorithm to obtain standard environmental data, it is possible to effectively reduce the interference of environmental noise on the data, enhance the accuracy of key signals, and thus improve the sensitivity and response speed of the monitoring system to environmental changes.

[0013] In one example, the present application can be further configured as: using a support vector machine algorithm to analyze the standard environmental data, and triggering a safety warning message when a sudden structural safety risk is identified, specifically including: Use the support vector machine algorithm to compare the standard environmental data with the normal state data threshold, and classify the standard environmental data according to the comparison result; Mark the standard environmental data that exceeds the normal state threshold as the sudden structural safety risk, trigger a safety warning message and send the specific risk type and location information.

[0014] By adopting the above technical solutions, by using the support vector machine algorithm to compare the standard environmental data with the normal state data threshold, and classifying the standard environmental data according to the comparison result, it is possible to identify normal and abnormal data, ensure the accuracy of risk detection, and thus effectively reduce the occurrence of false alarms and missed alarms; by marking the standard environmental data that exceeds the normal state threshold as a sudden structural safety risk, triggering a security warning message and sending specific risk type and location information, it is possible to timely notify relevant personnel to take countermeasures, ensure the efficiency of risk control, and thus improve the overall safety level of the building.

[0015] In one example, the present application can be further configured as follows: The construction of the preset safety prediction model specifically includes: Obtain historical structural multi-source data, and classify it according to the time characteristics and spatial characteristics of the historical structural multi-source data to generate a short-term sudden data set and a long-term trend data set; Based on the short-term sudden data set and the long-term trend data set, perform iterative training on a preset machine learning algorithm to obtain the safety prediction model.

[0016] By adopting the above technical solutions, by obtaining historical structural multi-source data and classifying it according to the time characteristics and spatial characteristics of the historical structural multi-source data to generate a short-term sudden data set and a long-term trend data set, it is possible to perform targeted processing on different types of data, ensure the diversity of model training data, and thus improve the accuracy and comprehensiveness of the prediction model; by performing iterative training on a preset machine learning algorithm based on the short-term sudden data set and the long-term trend data set to obtain a safety prediction model, it is possible to dynamically update the model to adapt to data changes, ensure the self-adaptability of the model, and thus improve the prediction ability of building structural safety risks and reduce the possibility of potential risks occurring.

[0017] The above second invention object of the present application is achieved by the following technical solutions: A safety risk prevention and control device for a building's exterior envelope structure, the safety risk prevention and control device for a building's exterior envelope structure includes: A three-dimensional modeling module, configured to obtain three-dimensional scan data of a building, and generate a three-dimensional structure model of the building according to the three-dimensional scan data through image recognition and three-dimensional modeling technologies; A structural feature extraction module, configured to extract the structural features of the building from the three-dimensional structure model, and based on the structural features, combine a clustering analysis algorithm to generate a corresponding environmental monitoring plan, and determine the acquisition location and data type of real-time environmental data; An environmental data acquisition module, configured to acquire the real-time environmental data of the exterior envelope structure, and perform dynamic filtering on the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; A risk analysis module, configured to analyze the standard environmental data by using a support vector machine algorithm, and trigger a safety warning message when a sudden structural safety risk is identified; A risk prediction module, configured to obtain multi-source structural data, predict the multi-source structural data by using a preset safety prediction model, obtain the development trend of the safety risk of the building structure, and estimate potential risks based on the development trend of the safety risk.

[0018] By adopting the above technical solutions, by obtaining the three-dimensional scan data of the building and generating the three-dimensional structure model of the building through image recognition and three-dimensional modeling technologies, the overall structure model of the building can be quickly constructed, ensuring comprehensive analysis of each part of the building, thereby improving the accuracy of data collection; by extracting the structural features of the building from the three-dimensional structure model and generating an environmental monitoring plan based on the structural features in combination with the clustering analysis algorithm, a monitoring plan suitable for different parts of the building can be automatically generated, reducing the errors caused by human intervention, thereby improving the accuracy and flexibility of monitoring; by collecting the real-time environmental data of the exterior enclosure structure and dynamically filtering the real-time environmental data based on the adaptive filtering algorithm to obtain the standard environmental data, the noise interference can be effectively filtered, improving the data quality, thereby ensuring the reliability of subsequent analysis; by analyzing the standard environmental data by using a support vector machine algorithm and triggering a safety warning message when a sudden structural safety risk is identified, sudden risks can be timely identified and fed back, ensuring the real-time nature of risk control, thereby reducing the impact of potential safety hazards.

[0019] The above object three of the present application is achieved by the following technical solutions: A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the above method for preventing and controlling the safety risk of the building exterior enclosure structure are implemented.

[0020] The above object four of the present application is achieved by the following technical solutions: A computer-readable storage medium, storing a computer program, wherein when the computer program is executed by a processor, the steps of the above method for preventing and controlling the safety risk of the building exterior enclosure structure are implemented.

[0021] In summary, the present application includes the following beneficial technical effects: 1. By acquiring the three-dimensional scanning data of a building and generating a three-dimensional structural model of the building through image recognition and three-dimensional modeling techniques, the overall structural model of the building can be quickly constructed, ensuring a comprehensive analysis of each part of the building, thereby improving the accuracy of data collection. By extracting the structural features of the building from the three-dimensional structural model and generating an environmental monitoring plan based on the structural features in combination with the clustering analysis algorithm, a monitoring plan suitable for different parts of the building can be automatically generated, reducing the errors caused by human intervention, thereby improving the accuracy and flexibility of monitoring. By collecting the real-time environmental data of the peripheral enclosure structure and dynamically filtering the real-time environmental data based on the adaptive filtering algorithm to obtain standard environmental data, the noise interference can be effectively filtered, improving the data quality, thereby ensuring the reliability of subsequent analysis. By using the support vector machine algorithm to analyze the standard environmental data and triggering a safety warning message when a sudden structural safety risk is identified, the sudden risk can be timely identified and feedback, ensuring the real-time nature of risk control, thereby reducing the impact of potential safety hazards. 2. By performing geometric analysis based on the three-dimensional structural model, extracting the geometric parameters of the load-bearing structure, exterior wall, and key nodes of the building, and conducting characteristic comparison and analysis of the geometric parameters in combination with the historical building structure database to identify structural features, the key features of the building structure can be deeply analyzed, providing basic data for subsequent monitoring, thereby improving the pertinence and accuracy of the building monitoring plan. By performing clustering analysis on the structural features of different parts of the building to determine the key monitoring areas, and dynamically setting the sensor sampling frequency and monitoring data type for different key monitoring areas, the monitoring plan can be dynamically adjusted according to the characteristics of each part of the building, optimizing the resource allocation, thereby improving the effectiveness of key area monitoring. 3. By obtaining the attribute parameters of building materials and determining the high thermal expansion coefficient areas and stress concentration areas according to the attribute parameters, the important areas of the building structure can be distinguished according to different material characteristics, ensuring the accuracy of the monitoring plan, thereby effectively improving the monitoring effect of key areas. By performing thermodynamic analysis and stress analysis to determine the thermal expansion areas and / or crack propagation areas, calculating the risk coefficients of each area, and determining the priority monitoring areas based on the risk coefficients, the high-risk areas can be preferentially monitored, reducing resource waste, thereby ensuring the reliability and timeliness of risk detection. Description of the Drawings

[0022] Figure 1 is a flowchart of a method for preventing and controlling safety risks of a building's peripheral enclosure structure in an embodiment of the present application; Figure 2 is a flowchart for implementing step S20 in a method for preventing and controlling safety risks of a building's peripheral enclosure structure in an embodiment of the present application; Figure 3 is a flowchart for implementing step S22 in a method for preventing and controlling safety risks of a building's peripheral enclosure structure in an embodiment of the present application; Figure 4 It is a flowchart of the implementation of step S30 in the method for preventing and controlling the safety risks of building envelopes in an embodiment of the present application; Figure 5 It is a flowchart of the implementation of step S40 in the method for preventing and controlling the safety risks of building envelopes in an embodiment of the present application; Figure 6 It is a flowchart of the implementation of the construction of the safety prediction model in the method for preventing and controlling the safety risks of building envelopes in an embodiment of the present application; Figure 7 It is a principle block diagram of a device for preventing and controlling the safety risks of building envelopes in an embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. Detailed implementation manners

[0023] The present application will be further described in detail below with reference to the accompanying drawings.

[0024] In one embodiment, as Figure 1 shown, the present application discloses a method for preventing and controlling the safety risks of building envelopes, which specifically includes the following steps: S10: Obtain the three-dimensional scan data of the building, and generate a three-dimensional structure model of the building according to the three-dimensional scan data and through image recognition and three-dimensional modeling technologies.

[0025] Specifically, when obtaining the three-dimensional scan data, high-resolution scans are performed using lidar or drones at different orientations of the building. The lidar device emits lasers and receives the reflected signals to obtain the fine point cloud data of the external structure of the building. The drone is equipped with a high-definition camera to obtain the image data of the top and surrounding facades of the building. After scanning, the point cloud data and image data at different angles are stitched through data fusion processing to obtain a complete three-dimensional image of the external structure of the building. Then, the image recognition algorithm is used to gradually process the scan data, extract the edges, corners, and key contours of the building, and on this basis, three-dimensional modeling is performed to convert the image information into three-dimensional coordinate data, and the overall three-dimensional structure model of the building is constructed through spatial interpolation of data points, thereby laying a foundation for the extraction and analysis of structural features in the subsequent steps.

[0026] S20: Extract the structural features of the building from the three-dimensional structure model, and based on the structural features, generate a corresponding environmental monitoring plan in combination with the clustering analysis algorithm, and determine the collection locations and data types of real-time environmental data.

[0027] Specifically, when extracting structural features from a three-dimensional structural model, the geometric parameters of each building component in the model are first calculated, including information such as the size, angle, surface area and volume of each component, and these parameters are recorded as the geometric features of each part of the building. Then, a feature extraction algorithm is used to analyze the spatial distribution relationship of different parts in the model, and the specific location and size information of the building's load-bearing walls, exterior walls, pillars and key connection nodes are identified. In combination with the database of historical building structures, the standardization and safety of each component are verified through comparative analysis to ensure that the structural information in the model is accurate and reliable. When generating an environmental monitoring plan based on these structural features, a cluster analysis algorithm is used to divide the building into different monitoring areas. By analyzing the characteristic information of each area and its sensitivity to changes in the external environment, the type of real-time environmental data and the sensor layout location that should be collected in each area are determined. For example, stress and deformation data are collected first in pillar areas with higher loads, and temperature and humidity data are collected first in exterior walls and window areas, thereby providing accurate guidance for subsequent real-time monitoring.

[0028] S30: Collecting real-time environmental data of the external protective structure, and dynamically filtering the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data.

[0029] Specifically, during the real-time environmental data collection process, data is collected through sensors installed in key positions of the building's exterior envelope structure, including temperature sensors, humidity sensors, stress sensors, etc. These sensors record and transmit environmental changes in real time. In order to avoid the impact of data fluctuations caused by external interference on the analysis results, an adaptive filtering algorithm is used to filter the collected data in real time. The adaptive filtering algorithm automatically adjusts the filtering parameters according to the volatility and trend of the current data, and adjusts the gain and window size of the filter by detecting the instantaneous change rate and stability of the data to ensure the effectiveness of the filtering. For example, when a significant change in ambient temperature is detected, the window is reduced to capture real-time changes. When the environment is detected to be stable, the window is expanded to enhance data smoothness. Finally, standard environmental data that has been processed with noise suppression and signal enhancement is obtained, providing a reliable data basis for subsequent analysis.

[0030] S40: Use the support vector machine algorithm to analyze the standard environmental data and trigger a safety warning message when a sudden structural safety risk is identified.

[0031] Specifically, when analyzing the standard environmental data through the support vector machine algorithm, the real-time collected standard environmental data is input into the trained support vector machine model. The model classifies and judges the current environmental data according to the thresholds of the defined normal state data and abnormal state data. The support vector machine algorithm conducts risk assessment based on the distance between the input data and the classification plane in the training samples. When the characteristics of the input data exceed the range of the normal state data and approach or exceed the threshold boundary, the model marks it as abnormal, determines that there is a sudden structural safety risk, and immediately generates a safety warning message. The warning message includes the specific risk type and occurrence location to ensure that the monitoring personnel can receive the warning information in time and take corresponding safety measures promptly.

[0032] S50: Obtain the structural multi-source data, use the preset safety prediction model to predict the structural multi-source data, obtain the development trend of the safety risk of the building structure, and estimate the potential risk based on the development trend of the safety risk.

[0033] Specifically, when obtaining the structural multi-source data, by integrating data sources from different channels, including historical monitoring data, current environmental data, climate change data, and scenario perception data, the multi-source data is formatted to ensure data consistency. Subsequently, the multi-source data is input into the safety prediction model. The model identifies the risk development trend of the building structure under different environmental conditions based on the analysis results of short-term and long-term trend data. The safety prediction model conducts iterative analysis on these data through machine learning algorithms and continuously optimizes the prediction results. When training the model, the short-term sudden data set is used to identify possible sudden risk characteristics, and the long-term trend data set is used to identify the change trend of potential risks. According to the prediction results, the possible risks in the key areas of the building structure in the future are analyzed, and the distribution of the risk levels is drawn based on the risk trend chart to provide intuitive warnings and risk assessment suggestions for building safety management.

[0034] In one embodiment, as Figure 2 shown, in step S20, that is, extract the structural characteristics of the building from the three-dimensional structural model, and based on the structural characteristics, generate an environmental monitoring plan in combination with the clustering analysis algorithm, specifically including: S21: Conduct geometric analysis based on the three-dimensional structural model, extract the geometric parameters of the load-bearing structure, exterior wall, and key nodes of the building, and conduct feature comparison and analysis on the geometric parameters in combination with the historical building structure database to identify the structural characteristics.

[0035] Specifically, by analyzing the geometric features of the three-dimensional structure model, geometric parameters of different components of the building are extracted. Dimension parameters such as the width, height, thickness, and volume of the load-bearing structure are calculated separately, and the areas and positions of the surfaces of each exterior wall are recorded. In addition, for key nodes of the structure such as joints, node coordinates and connection angles are extracted. The obtained geometric parameters are compared with the standard parameters in the historical database to identify and judge the types, positions, and safety of these structural components. If there are obvious abnormal changes in some structural features, such as the thickness of the load-bearing wall being lower than the normal value, the system can identify that there are potential risks in this area and mark them.

[0036] S22: By performing cluster analysis on the structural features of different parts of the building, key monitoring areas are determined, and for different key monitoring areas, the sensor sampling frequency and the types of monitoring data are dynamically set.

[0037] Specifically, by performing cluster analysis on the structural features of different parts, according to the attribute parameters of building materials and the distribution of structural features, the building is divided into multiple monitoring areas. The clustering features of each area include material type, location, and sensitivity to environmental changes. A higher temperature monitoring frequency is set for areas with a higher coefficient of thermal expansion, stress and deformation data are preferentially collected for areas with concentrated stress, and the sensor sampling frequency is dynamically increased during the monitoring of crack propagation areas, so as to ensure that environmental changes in key areas can be quickly detected and transmitted to the system for real-time analysis.

[0038] In one embodiment, as Figure 3 shown, in step S10, that is, by performing cluster analysis on the structural features of different parts of the building, it specifically includes: S221: Obtain the attribute parameters of building materials, and determine the areas with high coefficients of thermal expansion and areas with concentrated stress according to the attribute parameters.

[0039] Specifically, by analyzing the attribute parameter database of building materials, characteristics such as the coefficient of thermal expansion, compressive strength, and tensile strength of different materials are classified and marked. Areas with materials having a higher coefficient of thermal expansion, such as steel bars and glass, are identified as temperature-sensitive areas, and the main load-bearing components are identified as areas with concentrated stress. Detailed stress analysis and material property tests are carried out in areas with concentrated stress. By combining material properties with structural mechanics characteristics, areas in the building where thermal expansion or stress concentration may occur are determined, providing a basis for setting subsequent monitoring parameters.

[0040] S222: Determine the thermal expansion areas and / or crack propagation areas through thermodynamic analysis and stress analysis, calculate the risk coefficients of each area, and determine the priority monitoring areas based on the risk coefficients.

[0041] Specifically, by means of thermodynamic analysis, calculate the thermal expansion amounts of different parts of the building under temperature change conditions, focus on monitoring the influence of temperature on the structural stability of the material areas with high thermal expansion coefficients, analyze the stress conditions of the building's load-bearing components in stress analysis, and particularly pay attention to the stress distribution and stress change rate at the stress concentration parts. Mark the parts with higher stress concentration as potential areas for crack propagation. When calculating the risk coefficients for each area, assign different weights according to the thermal expansion and stress concentration conditions to obtain the comprehensive risk coefficients, and give priority to monitoring the areas with high risk coefficients to improve the accuracy and pertinence of the monitoring plan.

[0042] In one embodiment, as Figure 4 shown, in step S10, that is, collect the real-time environmental data of the peripheral enclosure structure, and dynamically filter the real-time environmental data based on the adaptive filtering algorithm to obtain the standard environmental data, which specifically includes: S31: According to the change situation of the real-time environmental data, dynamically adjust the filtering parameters to eliminate the invalid data affected by external interference.

[0043] Specifically, when the change of the real-time environmental data is large, increase the sensitivity of the data by adaptively adjusting the filtering parameters. For example, when the external temperature changes sharply, shorten the filtering window to enhance the response ability to the mutant data. While when the environment is relatively stable, automatically widen the filtering window to smooth the data fluctuation, so as to ensure that the filtered data is both real-time and maintains a certain stability, eliminate the invalid data while ensuring the overall accuracy and continuity of the data, and provide a reliable data basis for subsequent analysis.

[0044] S32: Perform noise suppression and signal enhancement through the adaptive filtering algorithm to obtain the standard environmental data.

[0045] Specifically, gradually process the collected environmental data through the adaptive filtering algorithm to suppress the environmental noise and improve the clarity of the effective signal. For example, during the detection process, when encountering noise fluctuations caused by external interferences such as strong wind and mechanical vibration, the adaptive filter automatically adjusts the filtering coefficient to weaken the high-frequency noise signal and make the data stream smoother. In addition, amplify the key data through the gain adjustment function inside the algorithm to more accurately represent the actual stress conditions of the building structure and the environmental changes, and finally output the stable and enhanced standard environmental data.

[0046] In one embodiment, as Figure 5 shown, in step S40, that is, use the support vector machine algorithm to analyze the standard environmental data, and trigger a safety warning message when a sudden structural safety risk is identified, which specifically includes: S41: Use the support vector machine algorithm to compare the standard environmental data with the normal state data threshold, and classify the standard environmental data according to the comparison result.

[0047] Specifically, the standard environmental data is input into the trained support vector machine model and compared in real time with the threshold range of the normal state data. The support vector machine classifies the environmental data into normal and abnormal categories according to the data distribution, judges its risk level according to the degree of data deviation from the threshold, and judges the correlation between different data through the clustering analysis of each item of data. For example, when the stress data and humidity data are both abnormal, the data is marked as a higher risk level, providing a basis for early warning judgment.

[0048] S42: Mark the standard environmental data exceeding the normal state threshold as a sudden structural safety risk, trigger a safety warning message and send the specific risk type and location information.

[0049] Specifically, after the support vector machine model determines the abnormality, mark the abnormal data as a sudden structural safety risk, automatically generate a safety warning message through the warning mechanism. The message content includes the specific location where the risk occurs, the risk type, and a proposed preliminary treatment plan, and send the information to the monitoring terminal to prompt the monitoring personnel to quickly check the relevant parts, ensuring that the monitoring personnel can grasp the dynamic information of the sudden risk in the first time, so as to take timely countermeasures to reduce possible losses.

[0050] In one embodiment, as Figure 6 shown, in step S50, that is, the construction of the preset safety prediction model specifically includes: S501: Obtain the historical structural multi-source data, classify it according to the time characteristics and spatial characteristics of the historical structural multi-source data, and generate a short-term sudden data set and a long-term trend data set.

[0051] Specifically, through the time series analysis of the historical structural monitoring data, separate the sudden data that appears in a short time from the long-term changing data. The short-term sudden data set represents the high-frequency change characteristics such as stress concentration and sudden temperature change that may occur within a certain time range, and the long-term trend data set contains the stability trends of the building in terms of temperature, humidity, stress, etc. In addition, based on the spatial characteristics of different monitoring positions in the historical data, the data is assigned to the corresponding building area, so that the subsequent machine learning model can perform risk prediction more targeted.

[0052] S502: Iteratively train the preset machine learning algorithm based on the short-term sudden data set and the long-term trend data set to obtain a safety prediction model.

[0053] Specifically, by inputting short-term burst data and long-term trend data into a preset machine learning model for training, continuously updating model parameters during the training process, including learning rate, number of layers, number of neurons, etc., training the model to identify the characteristics of burst risks for short-term burst data, training the model to identify the development direction of potential risks for long-term trend data, and gradually iterating to optimize the model performance, so that the model has stronger prediction accuracy and stability for the safety risks of building structures, and can timely warn of potential risks in future practical applications.

[0054] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0055] In one embodiment, a safety risk prevention and control device for building envelopes is provided, and the safety risk prevention and control device for building envelopes corresponds one-to-one with the safety risk prevention and control method for building envelopes in the above embodiment. As Figure 7 shown, the safety risk prevention and control device for building envelopes includes a three-dimensional modeling module, a structural feature extraction module, an environmental data acquisition module, a risk analysis module, and a risk prediction module. The detailed description of each functional module is as follows: The three-dimensional modeling module is used to obtain the three-dimensional scan data of the building, and generate a three-dimensional structure model of the building according to the three-dimensional scan data and through image recognition and three-dimensional modeling techniques; The structural feature extraction module is used to extract the structural features of the building from the three-dimensional structure model, and based on the structural features, combine the clustering analysis algorithm to generate a corresponding environmental monitoring plan, and determine the acquisition location and data type of real-time environmental data; The environmental data acquisition module is used to collect the real-time environmental data of the outer envelope structure, and dynamically filter the real-time environmental data based on the adaptive filtering algorithm to obtain standard environmental data; The risk analysis module is used to analyze the standard environmental data using the support vector machine algorithm, and trigger a safety warning message when a sudden structural safety risk is identified; The risk prediction module is used to obtain the structural multi-source data, use a preset safety prediction model to predict the structural multi-source data, obtain the development trend of the safety risks of the building structure, and estimate potential risks based on the development trend of the safety risks.

[0056] Optionally, the structural feature extraction module specifically includes: The feature analysis sub-module is used to perform geometric analysis based on the three-dimensional structure model, extract the geometric parameters of the load-bearing structure, exterior wall and key nodes of the building, and perform feature comparison and analysis on the geometric parameters in combination with the historical building structure database to identify structural features; The monitoring plan generation sub-module is used to determine key monitoring areas by clustering and analyzing the structural characteristics of different parts of the building, and dynamically set the sensor sampling frequency and monitoring data types for different key monitoring areas.

[0057] Optionally, the monitoring plan generation sub-module specifically includes: The material property identification unit is used to obtain the property parameters of building materials and determine the high thermal expansion coefficient area and the stress concentration area according to the property parameters; The priority monitoring area determination unit is used to determine the thermal expansion area and / or crack propagation area through thermodynamic analysis and stress analysis, calculate the risk coefficient of each area, and determine the priority monitoring area based on the risk coefficient.

[0058] Optionally, the environmental data acquisition module specifically includes: The data filtering sub-module is used to dynamically adjust the filtering parameters according to the change of real-time environmental data and eliminate invalid data affected by external interference; The noise suppression sub-module is used to perform noise suppression and signal enhancement through an adaptive filtering algorithm to obtain standard environmental data.

[0059] Optionally, the risk analysis module specifically includes: The data classification sub-module is used to compare the standard environmental data with the normal state data threshold by using the support vector machine algorithm and classify the standard environmental data according to the comparison result; The early warning trigger sub-module is used to mark the standard environmental data exceeding the normal state threshold as a sudden structural safety risk, trigger a safety warning message and send specific risk type and location information.

[0060] Optionally, the risk prediction module specifically includes: The data classification generation sub-module is used to obtain historical structural multi-source data, classify it according to the time characteristics and spatial characteristics of the historical structural multi-source data, and generate a short-term sudden data set and a long-term trend data set; The model training sub-module is used to iteratively train a preset machine learning algorithm based on the short-term sudden data set and the long-term trend data set to obtain a safety prediction model.

[0061] For the specific limitations of the building envelope structure safety risk prevention and control device, reference can be made to the limitations of the building envelope structure safety risk prevention and control method in the above text, which will not be elaborated here. Each module in the above building envelope structure safety risk prevention and control device can be implemented in whole or in part by software, hardware and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0062] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structural diagram may be as shown in Figure 8 . The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for preventing and controlling the safety risks of building envelopes.

[0063] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: Obtain the three-dimensional scan data of a building, and generate a three-dimensional structure model of the building according to the three-dimensional scan data and through image recognition and three-dimensional modeling techniques; Extract the structural features of the building from the three-dimensional structure model, and based on the structural features, generate a corresponding environmental monitoring plan in combination with a clustering analysis algorithm, and determine the acquisition location and data type of real-time environmental data; Collect the real-time environmental data of the building envelope, and dynamically filter the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; Analyze the standard environmental data using a support vector machine algorithm, and trigger a safety warning message when a sudden structural safety risk is recognized; Obtain multi-source structure data, predict the multi-source structure data using a preset safety prediction model, obtain the development trend of the safety risks of the building structure, and estimate potential risks based on the development trend of the safety risks.

[0064] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented: Obtain the three-dimensional scan data of a building, and generate a three-dimensional structure model of the building according to the three-dimensional scan data and through image recognition and three-dimensional modeling techniques; Extract the structural features of the building from the three-dimensional structure model, and based on the structural features, generate a corresponding environmental monitoring plan in combination with a clustering analysis algorithm, and determine the acquisition location and data type of real-time environmental data; Collect the real-time environmental data of the building envelope, and dynamically filter the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; Analyze the standard environmental data using the support vector machine algorithm, and trigger a security warning message when a sudden structural safety risk is identified; Obtain multi-source data of the structure, use a preset safety prediction model to predict the multi-source data of the structure, obtain the development trend of the safety risk of the building structure, and estimate potential risks based on the development trend of the safety risk.

[0065] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0066] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0067] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for preventing and controlling safety risks of building envelope structures, characterized in that: The building envelope structure safety risk prevention and control method comprises: Acquire three-dimensional scanning data of a building, and generate a three-dimensional structural model of the building according to the three-dimensional scanning data by using image recognition and three-dimensional modeling technology; Extracting structural features of the building from the three-dimensional structural model, generating a corresponding environmental monitoring plan based on the structural features and combining a cluster analysis algorithm to determine the collection location and data type of real-time environmental data; Collecting the real-time environmental data of the external protective structure, and dynamically filtering the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; Using a support vector machine algorithm to analyze the standard environmental data, and triggering a safety warning message when a sudden structural safety risk is identified; Acquire multi-source structural data, use a preset safety prediction model to predict the multi-source structural data, obtain the safety risk development trend of the building structure, and estimate potential risks based on the safety risk development trend.

2. The method for preventing and controlling safety risks of building envelope structures according to claim 1 is characterized in that: The extracting the structural features of the building from the three-dimensional structural model and generating an environmental monitoring plan based on the structural features and in combination with a cluster analysis algorithm specifically includes: Performing geometric analysis based on the three-dimensional structural model, extracting geometric parameters of the load-bearing structure, exterior walls and key nodes of the building, performing feature comparison analysis on the geometric parameters in combination with a historical building structure database, and identifying the structural features; By clustering the structural features of different parts of the building, the key monitoring areas are determined, and the sensor sampling frequency and monitoring data type are dynamically set for different key monitoring areas.

3. The method for preventing and controlling safety risks of building envelope structures according to claim 2 is characterized in that: The cluster analysis of the structural features of different parts of the building specifically includes: Acquire property parameters of building materials, and determine high thermal expansion coefficient areas and stress concentration areas according to the property parameters; The thermal expansion area and / or the crack propagation area are determined by thermodynamic analysis and stress analysis, and the risk coefficient of each area is calculated, and the priority monitoring area is determined based on the risk coefficient.

4. The method for preventing and controlling safety risks of building envelope structures according to claim 1, characterized in that: The collecting of the real-time environmental data of the external protective structure and dynamically filtering the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data specifically includes: According to the changes in the real-time environmental data, the filtering parameters are dynamically adjusted to eliminate invalid data affected by external interference; The standard environment data is obtained by performing noise suppression and signal enhancement through an adaptive filtering algorithm.

5. The method for preventing and controlling safety risks of building envelope structures according to claim 1, characterized in that: The use of the support vector machine algorithm to analyze the standard environmental data and trigger a safety warning message when a sudden structural safety risk is identified specifically includes: Using the support vector machine algorithm to compare the standard environment data with the normal state data threshold, and classifying the standard environment data according to the comparison result; The standard environmental data exceeding the normal state threshold is marked as the sudden structural safety risk, triggering a safety warning message and sending specific risk type and location information.

6. The method for preventing and controlling safety risks of building envelope structures according to claim 1, characterized in that: The construction of the preset security prediction model specifically includes: Acquire historical structure multi-source data, and classify them according to the temporal characteristics and spatial characteristics of the historical structure multi-source poems to generate a short-term burst data set and a long-term trend data set; The preset machine learning algorithm is iteratively trained based on the short-term burst data set and the long-term trend data set to obtain the security prediction model.

7. A building exterior structure safety risk prevention and control device, characterized in that: The building exterior structure safety risk prevention and control device comprises: A three-dimensional modeling module, used to obtain three-dimensional scanning data of a building, and generate a three-dimensional structural model of the building according to the three-dimensional scanning data through image recognition and three-dimensional modeling technology; A structural feature extraction module is used to extract the structural features of the building from the three-dimensional structural model, generate a corresponding environmental monitoring plan based on the structural features and in combination with a cluster analysis algorithm, and determine the collection location and data type of real-time environmental data; An environmental data acquisition module is used to collect the real-time environmental data of the external protective structure, and dynamically filter the real-time environmental data based on an adaptive filtering algorithm to obtain standard environmental data; A risk analysis module, used to analyze the standard environmental data using a support vector machine algorithm and trigger a safety warning message when a sudden structural safety risk is identified; The risk prediction module is used to obtain multi-source structural data, use a preset safety prediction model to predict the multi-source structural data, obtain the safety risk development trend of the building structure, and estimate potential risks based on the safety risk development trend.

8. The building envelope structure safety risk prevention and control device according to claim 7 is characterized in that: The structural feature extraction module specifically includes: A feature analysis submodule is used to perform geometric analysis based on the three-dimensional structural model, extract geometric parameters of the load-bearing structure, exterior walls and key nodes of the building, perform feature comparison analysis on the geometric parameters in combination with a historical building structure database, and identify the structural features; The monitoring scheme generation submodule is used to determine the key monitoring areas by clustering analysis of the structural features of different parts of the building, and dynamically set the sensor sampling frequency and monitoring data type for different key monitoring areas.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for preventing and controlling safety risks of the building envelope structure as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for preventing and controlling safety risks of building envelope structures as described in any one of claims 1 to 6 are implemented.

Images