Method and device for safety appraisal of dangerous and old buildings

Abstract

The present application discloses a method and device for safety appraisal of dangerous and old buildings. By collecting the current situation data of the foundation, the main body, and building materials of the target building, and generating a digital current situation model of the target building based on the current situation data; using a building hazard simulation tool to collect the dynamic data of the target building under various hazard simulation projects; identifying the defect characteristic data of the target building according to the current situation data and the dynamic data; and using a preset building appraisal model to determine the building component appraisal result, the building partial appraisal result, and the building overall appraisal result based on the defect characteristic data, so as to be able to establish a digital model for testing when simulating a dangerous environment on the basis of the current situation data of the target building, thereby being able to collect the defense ability of the target building in a dangerous environment, and reducing the subjective factors of manual experience and the probability of data errors through model identification and appraisal, and improving the credibility of the appraisal result.

Description

Technical Field

[0001] This application relates to the technical field of building inspection, and particularly to a method and device for identifying the safety of dilapidated buildings. Background Art

[0002] With the acceleration of the urbanization construction process, the renovation project of urban dilapidated buildings has been put on the agenda, and the identification of dilapidated houses has also been taken seriously. At present, the identification of dilapidated houses mainly adopts the industry standard JGJ15-2016 "Standard for Identifying Dangerous Houses" for identification. Specifically, the on-site inspection of house components and instrument measurement are carried out manually, and the artificial identification and analysis are carried out by combining the hierarchical risk identification and the comprehensive proportion identification method of the overall structural dangerous components. However, the identification of house safety involves the influence of multiple factors and a large amount of data analysis. Currently, the linear analysis of measurement data is based on the work experience of the identification personnel, which has a large subjective factor and is prone to data omission or error, resulting in a low credibility of the identification result. Summary of the Invention

[0003] This application provides a method and device for identifying the safety of dilapidated buildings to solve the technical problem of low credibility of the current identification results of dilapidated houses.

[0004] To solve the above technical problems, in a first aspect, this application provides a method for identifying the safety of dilapidated buildings, including:

[0005] Collect the current situation data of the target building, and use a building modeling tool to generate a digital current situation model of the target building based on the current situation data, where the current situation data includes foundation current situation data, main body current situation data, and building material current situation data;

[0006] Use a building hazard simulation tool to conduct a simulation test on the digital current situation model of the target building to collect the dynamic data of the target building under each hazard simulation project;

[0007] Identify the defect feature data of the target building according to the current situation data and the dynamic data;

[0008] Use a preset building identification model to conduct a safety identification of the target building according to the defect feature data to obtain an identification result, where the identification result includes building component identification results, building partial identification results, and building overall identification results.

[0009] In some of these embodiments, the collecting the current situation data of the target building includes:

[0010] Detect the foundation current situation data of the target building through a ground penetrating radar;

[0011] Scan the main body current situation data of the target building through a laser scanner;

[0012] Using an ultrasonic detector, detect the current status data of the building materials of the target building, where the current status data of the building materials includes the current status data of masonry, the current status data of concrete, the current status data of wooden components, and the current status data of steel components.

[0013] In some embodiments, using a building modeling tool, based on the current status data, generate a digital current status model of the target building, including:

[0014] Convert the current status data into file data in a format corresponding to the building modeling tool, and import the file data into the building modeling tool;

[0015] Through the building modeling tool, according to the current status data of the main body and the current status data of the foundation, automatically generate a three-dimensional solid model of the target building, where the three-dimensional solid model includes an internal structure sub-model and a surface structure sub-model;

[0016] Based on the current status data of the building materials, add material attribute information to the three-dimensional solid model to generate the digital current status model.

[0017] In some embodiments, using a building hazard simulation tool, perform a simulation test on the digital current status model of the target building to collect dynamic data of the target building under various hazard simulation projects, including:

[0018] Using the building hazard simulation tool, configure virtual sensors at multiple key components, multiple building layers, and key points corresponding to the overall building in the digital current status model;

[0019] Simulate the hazard environment of the digital current status model, and collect dynamic data of multiple key components, multiple building layers, and the overall building of the target building respectively in the hazard environment through the virtual sensors, where the hazard environment includes an earthquake environment, a rain and flood environment, and a high temperature environment.

[0020] In some embodiments, according to the current status data and the dynamic data, identify the defect feature data of the target building, including:

[0021] Using a preset building defect identification model, according to the current status data of the foundation, the current status data of the main body, and the current status data of the building materials, identify the surface defect feature data and internal defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively;

[0022] Using a preset building defect identification model, based on the dynamic data, identify the potential defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building; the preset building defect identification model is a deep learning model trained with current situation data samples and dynamic data samples after sample annotation based on preset building appraisal criteria.

[0023] In some of these embodiments, using the preset building appraisal model, based on the defect feature data, conduct a safety appraisal of the target building to obtain an appraisal result, including:

[0024] Using the preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data of multiple key components of the target building, conduct a safety appraisal of each key component to obtain the building component appraisal result;

[0025] Using the preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data of multiple building layers of the target building and the building component appraisal result, conduct a safety appraisal of each building layer to obtain the building partial appraisal result;

[0026] Using the preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data corresponding to multiple key points of the target building and the building layer appraisal result, conduct a safety appraisal of the whole building to obtain the building overall appraisal result.

[0027] In some of these embodiments, the preset building appraisal model is a classification model trained with defect feature data samples after sample annotation based on preset building appraisal criteria.

[0028] In a second aspect, the present application also provides a safety appraisal device for dilapidated buildings, including:

[0029] A collection module for collecting the current situation data of the target building

[0030] A modeling module for using a building modeling tool to generate a digital current situation model of the target building based on the current situation data, where the current situation data includes foundation current situation data, main body current situation data, and building material current situation data;

[0031] A simulation module for using a building hazard simulation tool to conduct a simulation test on the digital current situation model of the target building to collect the dynamic data of the target building under various hazard simulation projects;

[0032] An identification module for identifying the defect feature data of the target building based on the current situation data and the dynamic data

[0033] An identification module, configured to use a preset building identification model to perform a safety identification on the target building according to the defect feature data, and obtain an identification result, where the identification result includes a building component identification result, a building partial identification result, and a building overall identification result.

[0034] In a third aspect, the present application further provides a computer device, including a processor and a memory, where the memory is used to store a computer program, and when the computer program is executed by the processor, it implements the method for identifying the safety of dilapidated buildings as described in the first aspect.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the method for identifying the safety of dilapidated buildings as described in the first aspect.

[0036] Compared with the prior art, the present application at least has the following beneficial effects:

[0037] By collecting the foundation status data, main body status data, and building material status data of the target building, and using a building modeling tool, a digital status model of the target building is generated based on the status data; using a building hazard simulation tool to perform a simulation test on the digital status model of the target building to collect the dynamic data of the target building under each hazard simulation project; identifying the defect feature data of the target building according to the status data and the dynamic data; using a preset building identification model to perform a safety identification on the target building according to the defect feature data, and obtaining a building component identification result, a building partial identification result, and a building overall identification result, so as to be able to establish a digital model for testing when simulating a dangerous environment based on the status data of the target building, thereby being able to collect the defense ability of the target building in a dangerous environment, and reducing the subjective factors of manual experience and the probability of data errors through model identification and identification, and improving the credibility of the identification result. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic flowchart of the method for identifying the safety of dilapidated buildings shown in the embodiments of the present application;

[0039] Figure 2 It is a schematic structural diagram of the device for identifying the safety of dilapidated buildings shown in the embodiments of the present application;

[0040] Figure 3 It is a schematic structural diagram of the computer device shown in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0042] As recorded in the related art, the current identification of dangerous and old houses needs to be based on the work experience of the appraisers and combined with linear analysis of the measurement data, which has a large subjective factor and is prone to data omission or error, resulting in a low credibility of its identification results.

[0043] To this end, the present application collects the current situation data of the foundation, the current situation data of the main body, and the current situation data of the building materials of the target building, and uses a building modeling tool to generate a three-dimensional model of the target building based on the current situation data; imports the model file of the three-dimensional model into a building hazard simulation tool to perform a simulation test on the three-dimensional model of the target building to collect the dynamic data of the target building under each hazard simulation project; then imports the current situation data and the dynamic data into a preset building defect identification model, and the preset building defect identification model outputs the defect feature data of the target building; finally, imports the defect feature data into a preset building identification model, and the preset building identification model outputs the building component identification result, the building partial identification result, and the building overall identification result, so as to be able to simulate the dynamic data of the target building in different dangerous environments and be able to analyze the non-linear potential defect feature data of the dynamic data through an artificial intelligence model, thereby analyzing the defense ability of the target building in the actual dangerous environment. Compared with the related linear calculation, the present application has higher accuracy and credibility; at the same time, the present application uses the artificial intelligence model to assist in identification and appraisal from multiple dimensions of components, building floors, and the building as a whole, without relying on manual experience and reducing manual operations, effectively reducing the subjective factor of manual experience and reducing the probability of data errors, and further improving the credibility of the identification results.

[0044] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for identifying the safety of dangerous and old buildings provided by an embodiment of the present application. The method for identifying the safety of dangerous and old buildings in the embodiments of the present application can be applied to computer devices, and the computer devices include but are not limited to devices such as laptop computers, tablet computers, desktop computers, physical servers, and cloud servers. As Figure 1 shown, the method for identifying the safety of dangerous and old buildings in this embodiment includes steps S101 to S105, which are described in detail as follows:

[0045] Step S101, collect the current situation data of the target building, and use a building modeling tool to generate a digital current situation model of the target building based on the current situation data. The current situation data includes foundation current situation data, main body current situation data, and building material current situation data.

[0046] In this step, the foundation current situation data includes, but is not limited to, the stratum sequence structure of the foundation, the groundwater level, the data of underground structures, the cavities and cracks in the foundation, the settlement and deformation of the foundation, and the density and humidity of the soil; the main body current situation data includes, but is not limited to, the geometric shape, dimensions and distances, structural layout, light and shadow, and reflection information; the building material current situation data includes masonry current situation data, concrete current situation data, wooden member current situation data, and steel member current situation data. The masonry current situation data includes, but is not limited to, masonry cracks and cavities, density, and the quality of masonry joints. The concrete current situation data includes, but is not limited to, internal cracks and cavities, concrete strength, density, and uniformity; the wooden member current situation data includes, but is not limited to, the internal decay of wood, density, stress, and deformation; the steel member current situation data includes, but is not limited to, internal cracks and weld defects, thickness, and corrosion conditions.

[0047] Optionally, detect the foundation current situation data of the target building through a ground penetrating radar; scan the main body current situation data of the target building through a laser scanner; detect the building material current situation data of the target building through an ultrasonic detector. The ground penetrating radar, laser scanner, and ultrasonic detector are all non-destructive tests to protect the building body.

[0048] Optionally, the building modeling tool includes Revit, SketchUp, Archicad, AutoCAD, Bentley OpenBuildings Designer, MicroStation, Dynascape, Rhino, BIMx, PlanGrid, etc. The above building modeling tools have an automatic modeling function or can expand the automatic modeling function through plug-ins. For example, Grasshopper is an automatic modeling plug-in for Rhino.

[0049] In some embodiments, convert the current situation data into file data in a format corresponding to the building modeling tool, and import the file data into the building modeling tool; through the building modeling tool, automatically generate a three-dimensional solid model of the target building according to the main body current situation data and the foundation current situation data. The three-dimensional solid model includes an internal structure sub-model and a surface structure sub-model; based on the building material current situation data, add the material attribute information of the three-dimensional solid model to generate the digital current situation model.

[0050] In this embodiment, by establishing an internal structure sub-model and a surface structure sub-model of the target building, and adding material property information, the surface defects and internal defects of the target building can be more clearly characterized, so that the structural status of the target building can be more accurately characterized.

[0051] Step S102: Use a building hazard simulation tool to perform a simulation test on the digital status model of the target building to collect dynamic data of the target building under various hazard simulation items.

[0052] In this step, the dynamic data is curve data collected by sensors over a period of time, such as the curve data of the building inclination changing with time. The building hazard simulation tool can be a functional plug-in in a building modeling tool or software such as SAP2000 or BIM. The hazard simulation items include, but are not limited to, earthquake environment simulation items, rainstorm and flood environment simulation items, high-temperature environment simulation items, and low-temperature environment simulation items, etc. By using the building hazard simulation tool to simulate the building dynamic data of the target building under different hazard environments, the data characterizing the seismic resistance, flood resistance, and thermal bridge phenomenon of the target building can be collected, thereby improving the safety appraisal result of the target building.

[0053] In some embodiments, step S102 includes:

[0054] Use the building hazard simulation tool to configure virtual sensors at multiple key components, multiple building floors, and key points corresponding to the overall building in the digital status model;

[0055] Simulate the hazard environment of the digital status model, and collect the dynamic data of multiple key components, multiple building floors, and the overall building of the target building under the hazard environment through the virtual sensors. The hazard environment includes earthquake environment, rainstorm and flood environment, and high-temperature environment.

[0056] In this embodiment, the virtual sensors include, but are not limited to, vibration sensors, tilt sensors, strain sensors, acceleration sensors, temperature sensors, etc. When the building hazard simulation tool simulates the hazard environment, the virtual sensors record the curve data of key components, building floors, and the overall building from the start of the environment simulation to the collapse of the building. For the high-temperature environment, sunlight is used as the heat source, and the simulation is carried out with reference to the orientation of the target building and the surrounding obstacles, and the temperature change on the surface of the target building is detected to detect whether there is a thermal bridge phenomenon or heat loss problem in the target building. It should be noted that the virtual sensors can be automatically configured according to preset rules, and then the installation position and type of the virtual sensors can be manually adjusted.

[0057] In this embodiment, by simulating the states of the target building under different dangerous environments, the various risk prevention capabilities of the target building can be more accurately identified. Compared with the current technology that performs linear analysis by collecting on-site data, this embodiment can uncover potential defects of the target building that cannot be obtained through linear analysis, improving the accuracy and credibility of the safety identification of the target building.

[0058] Step S103: Identify the defect feature data of the target building according to the current situation data and the dynamic data.

[0059] In this step, based on the preset building identification criteria, the current situation data and the dynamic data can be discriminated and classified to obtain the defect feature data. For example, for house identification, the preset building identification criteria can be identification specifications such as the industry standard JGJ15-2016 "Standard for Identifying Dangerous Houses". An artificial intelligence model can also be used to learn the current situation data and the dynamic data to extract the feature data related to the defect features in the current situation data and the dynamic data.

[0060] In some embodiments, step S103 includes:

[0061] Using a preset building defect identification model, according to the current situation data of the foundation, the current situation data of the main body, and the current situation data of the building materials, identify the surface defect feature data and the internal defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively;

[0062] Using a preset building defect identification model, according to the dynamic data, identify the potential defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively; the preset building defect identification model is a deep learning model trained with the current situation data samples and the dynamic data samples labeled based on the preset building identification criteria.

[0063] In this embodiment, the preset building defect identification model specifically includes a surface defect identification sub-model, an internal defect identification sub-model, and a potential defect identification sub-model. The surface defect identification sub-model is used to identify the surface defect feature data of the building, the internal defect identification sub-model is used to identify the internal defect feature data of the building, and the potential defect identification sub-model is used to identify the potential defect feature data of the building. The preset building defect identification model in this embodiment is essentially a feature extraction model, which can be constructed based on artificial intelligence algorithms such as convolutional neural networks, generative adversarial networks, autoencoders, and recurrent neural networks. Specifically, the surface defect identification sub-model and the internal defect identification sub-model in this embodiment are constructed using convolutional neural networks to be able to extract the deep features of the building current situation data; the potential defect identification sub-model uses a recurrent neural network to be able to extract the temporal features of the dynamic data.

[0064] In this embodiment, the defect feature data of the target building is extracted by a deep learning model, without relying on manual experience for linear analysis. Moreover, compared with the shallow features obtained by linear analysis, the deep learning model can extract the deep features of the defects of the target building, improving the identification accuracy.

[0065] Step S104: Use a preset building identification model to perform a safety identification on the target building according to the defect feature data, and obtain an identification result, where the identification result includes a building component identification result, a building local identification result, and a building overall identification result.

[0066] In this step, the preset building identification model can be a multi-classification model, specifically a multi-classification fusion model for building component identification, building local identification, and building overall identification, such as a decision tree model, a random forest model, and a neural network model, etc. It can be understood that a building layer is composed of general components and key components, and a building overall is composed of multiple building layers. Therefore, during the identification process of a building layer, the preset building identification model also considers the building component identification results related to the building layer. During the identification process of the building overall, the preset building identification model also considers the identification results of each building layer, thereby further improving the identification accuracy.

[0067] In some of the embodiments, step S104 includes:

[0068] Use a preset building identification model to perform a safety identification on each of the key components according to the surface defect feature data, internal defect feature data, and potential feature data of the multiple key components of the target building, and obtain the building component identification result;

[0069] Use a preset building identification model to perform a safety identification on each of the building layers according to the surface defect feature data, internal defect feature data, and potential feature data of the multiple building layers of the target building and the building component identification result, and obtain the building local identification result;

[0070] Use a preset building identification model to perform a safety identification on the building overall according to the surface defect feature data, internal defect feature data, and potential feature data corresponding to the multiple key points of the target building and the building layer identification result, and obtain the building overall identification result.

[0071] In this embodiment, the preset building identification model is a classification model trained with defect feature data samples labeled based on preset building identification criteria. This embodiment adopts a fusion model based on decision trees. Specifically, based on the decision tree, the identification results of each building component are output according to the defect feature data. The identification results of the building components and the defect feature data related to building stratification are used as the root nodes of the building stratification, and the identification results of each building stratification are output; the identification results of the building stratification and the defect feature data related to the whole building (such as structural connection defects between adjacent building stratifications) are used as the root nodes of the whole building, and the identification results of the whole building are output. In this embodiment, safety identification is performed through the model to eliminate subjective factors brought by manual experience and improve the credibility of the identification results.

[0072] To execute the safety identification method for dilapidated buildings corresponding to the above method embodiments to achieve the corresponding functions and technical effects. Refer to Figure 2 , Figure 2 FIG. shows a structural block diagram of a safety identification device for dilapidated buildings provided by an embodiment of the present application. For ease of explanation, only the parts related to this embodiment are shown. The safety identification device for dilapidated buildings provided by the embodiment of the present application includes:

[0073] An acquisition module 201, configured to acquire the current situation data of the target building

[0074] A modeling module 202, configured to use a building modeling tool to generate a digital current situation model of the target building based on the current situation data, where the current situation data includes foundation current situation data, main body current situation data, and building material current situation data;

[0075] A simulation module 203, configured to use a building hazard simulation tool to perform a simulation test on the digital current situation model of the target building to acquire dynamic data of the target building under each hazard simulation project;

[0076] An identification module 204, configured to identify defect feature data of the target building according to the current situation data and the dynamic data;

[0077] An identification module 205, configured to use a preset building identification model to perform safety identification on the target building according to the defect feature data to obtain an identification result, where the identification result includes building component identification results, building partial identification results, and building overall identification results.

[0078] In some embodiments, the acquisition module 201 is specifically configured to:

[0079] Detect the foundation current situation data of the target building through a ground penetrating radar;

[0080] Scan the main body current situation data of the target building through a laser scanner;

[0081] Detect the current status data of the building materials of the target building through an ultrasonic detector, where the current status data of the building materials includes the current status data of masonry, the current status data of concrete, the current status data of wooden components, and the current status data of steel components.

[0082] In some embodiments, the modeling module 202 is specifically configured to:

[0083] Convert the current status data into file data conforming to the corresponding format of the building modeling tool, and import the file data into the building modeling tool;

[0084] Through the building modeling tool, automatically generate a three-dimensional solid model of the target building according to the current status data of the main body and the current status data of the foundation, where the three-dimensional solid model includes an internal structure sub-model and a surface structure sub-model;

[0085] Based on the current status data of the building materials, add the material attribute information of the three-dimensional solid model to generate the digital current status model.

[0086] In some embodiments, the simulation module 203 is specifically configured to:

[0087] Use the building hazard simulation tool to configure virtual sensors at multiple key components, multiple building layers, and key points corresponding to the whole building in the digital current status model;

[0088] Simulate the dangerous environment of the digital current status model, and collect the dynamic data of multiple key components, multiple building layers, and the whole building of the target building respectively in the dangerous environment through the virtual sensors, where the dangerous environment includes an earthquake environment, a rain and flood environment, and a high temperature environment.

[0089] In some embodiments, the recognition module 204 is specifically configured to:

[0090] Use a preset building defect recognition model to identify the surface defect feature data and internal defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively according to the current status data of the foundation, the current status data of the main body, and the current status data of the building materials;

[0091] Use a preset building defect recognition model to identify the potential defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively according to the dynamic data; the preset building defect recognition model is a deep learning model trained with current status data samples and dynamic data samples labeled based on preset building appraisal standards.

[0092] In some embodiments, the appraisal module 205 is specifically configured to:

[0093] Using a preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data of multiple key components of the target building, conduct safety appraisals on each of the key components to obtain the building component appraisal results;

[0094] Using a preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data of multiple building layers of the target building, as well as the building component appraisal results, conduct safety appraisals on each of the building layers to obtain the building partial appraisal results;

[0095] Using a preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data corresponding to multiple key points of the target building, as well as the building layer appraisal results, conduct a safety appraisal on the overall building to obtain the overall building appraisal results.

[0096] In some embodiments, the preset building appraisal model is a classification model trained using a defect feature data sample that has been labeled based on a preset building appraisal standard.

[0097] The above-mentioned dilapidated building safety appraisal device can implement the dilapidated building safety appraisal method of the above method embodiments. The optional items in the above method embodiments are also applicable to this embodiment, and will not be elaborated here. The remaining content of the embodiments of the present application can refer to the content of the above method embodiments and will not be repeated in this embodiment.

[0098] Figure 3 This is a schematic structural diagram of a computer device provided in an embodiment of the present application. As Figure 3 shown, the computer device 3 in this embodiment includes: at least one processor 30 ( Figure 3 only one is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. When the processor 30 executes the computer program 32, it implements the steps in any of the above method embodiments.

[0099] The computer device 3 can be a computing device such as a smart phone, a tablet computer, a desktop computer, and a cloud server. The computer device may include, but is not limited to, the processor 30 and the memory 31. Those skilled in the art can understand that Figure 3 this is only an example of the computer device 3 and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0100] The so-called processor 30 may be a Central Processing Unit (CPU), and the processor 30 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0101] In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device 3. Further, the memory 31 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 31 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0102] In addition, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0103] An embodiment of the present application provides a computer program product, and when the computer program product runs on a computer device, the computer device is caused to implement the steps in each of the above method embodiments when executed.

[0104] In several embodiments provided by the present application, it can be understood that each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, the program segment, or the part of code includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.

[0105] If the described functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0106] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present application. It should be understood that the above description is only for the specific embodiments of the present application and is not used to limit the protection scope of the present application. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for safety appraisal of dangerous and old buildings, characterized in that Including: Collecting the current situation data of the target building, and using a building modeling tool to generate a digital current situation model of the target building based on the current situation data, where the current situation data includes foundation current situation data, main body current situation data, and building material current situation data; Using a building hazard simulation tool to perform a simulation test on the digital current situation model of the target building to collect the dynamic data of the target building under various hazard simulation projects; Identifying the defect feature data of the target building according to the current situation data and the dynamic data; Using a preset building appraisal model to perform a safety appraisal on the target building according to the defect feature data to obtain an appraisal result, where the appraisal result includes a building component appraisal result, a building partial appraisal result, and a building overall appraisal result; The step of using a building hazard simulation tool to perform a simulation test on the digital current situation model of the target building to collect the dynamic data of the target building under various hazard simulation projects includes: Using the building hazard simulation tool to configure virtual sensors at multiple key components, multiple building layers, and key points corresponding to the overall building in the digital current situation model; Simulating the hazard environment of the digital current situation model, and collecting the dynamic data of multiple key components, multiple building layers, and the overall building of the target building respectively in the hazard environment through the virtual sensors, where the hazard environment includes an earthquake environment, a rain and flood environment, and a high temperature environment; Identifying the defect feature data of the target building according to the current situation data and the dynamic data includes: Using a preset building defect identification model to identify the surface defect feature data and internal defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively according to the foundation current situation data, the main body current situation data, and the building material current situation data; Using a preset building defect identification model to identify the potential defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively according to the dynamic data; the preset building defect identification model is a deep learning model trained with current situation data samples and dynamic data samples labeled based on a preset building appraisal standard; The step of using a preset building appraisal model to perform a safety appraisal on the target building according to the defect feature data to obtain an appraisal result includes: Using a preset building appraisal model to perform a safety appraisal on each of the key components according to the surface defect feature data, internal defect feature data, and potential feature data of multiple key components of the target building to obtain the building component appraisal result; Using a preset building appraisal model to perform a safety appraisal on each of the building layers according to the surface defect feature data, internal defect feature data, and potential feature data of multiple building layers of the target building and the building component appraisal result to obtain the building partial appraisal result; Using a preset building appraisal model, based on the surface defect feature data, internal defect feature data, and potential feature data corresponding to multiple key points of the target building, as well as the building layer-by-layer appraisal results, conduct a safety appraisal of the entire building to obtain the overall building appraisal result.

2. The safety appraisal method for dilapidated buildings according to claim 1, wherein The collection of the current situation data of the target building includes: Detect the current situation data of the foundation of the target building through a ground penetrating radar. Scan the current situation data of the main body of the target building through a laser scanner. Detect the current situation data of the building materials of the target building through an ultrasonic detector, and the current situation data of the building materials includes the current situation data of masonry, the current situation data of concrete, the current situation data of wooden components, and the current situation data of steel components.

3. The safety appraisal method for dilapidated buildings according to claim 1, characterized in that, The use of a building modeling tool to generate a digital current situation model of the target building based on the current situation data includes: Convert the current situation data into file data in a format corresponding to the building modeling tool, and import the file data into the building modeling tool. Through the building modeling tool, automatically generate a three-dimensional solid model of the target building according to the current situation data of the main body and the current situation data of the foundation. The three-dimensional solid model includes an internal structure sub-model and a surface structure sub-model. Based on the current situation data of the building materials, add the material attribute information of the three-dimensional solid model to generate the digital current situation model.

4. The method for identifying the safety of dilapidated buildings according to claim 1, wherein, The preset building appraisal model is a classification model obtained by training a sample of defect feature data labeled based on a preset building appraisal standard.

5. An identification device for the safety of dilapidated buildings, characterized in that, It includes: A collection module for collecting the current situation data of the target building. A modeling module for using a building modeling tool to generate a digital current situation model of the target building based on the current situation data. The current situation data includes the current situation data of the foundation, the current situation data of the main body, and the current situation data of the building materials. A simulation module for using a building hazard simulation tool to conduct a simulation test on the digital current situation model of the target building to collect the dynamic data of the target building under various hazard simulation projects. An identification module for identifying the defect feature data of the target building according to the current situation data and the dynamic data. An appraisal module for using a preset building appraisal model to conduct a safety appraisal of the target building according to the defect feature data to obtain an appraisal result. The appraisal result includes the building component appraisal result, the building local appraisal result, and the building overall appraisal result. The simulation module is specifically used for: Using the building hazard simulation tool to configure virtual sensors at multiple key components, multiple building layers, and key points corresponding to the entire building in the digital current situation model. Simulate the dangerous environment of the digital current situation model, and collect the dynamic data of multiple key components, multiple building layers, and the entire building of the target building under the dangerous environment through the virtual sensors. The dangerous environment includes an earthquake environment, a rain and flood environment, and a high temperature environment. The identification module is specifically used for: Using a preset building defect recognition model, based on the current foundation data, the current main body data, and the current building material data, identify the surface defect feature data and the internal defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively; Using a preset building defect recognition model, based on the dynamic data, identify the potential defect feature data corresponding to multiple key components, multiple building layers, and multiple key points of the target building respectively; The preset building defect recognition model is a deep learning model trained with current situation data samples and dynamic data samples labeled based on preset building appraisal standards; The appraisal module is specifically used for: Using a preset building appraisal model, based on the surface defect feature data, the internal defect feature data, and the potential feature data of multiple key components of the target building, conduct safety appraisals on each of the key components to obtain the building component appraisal results; Using a preset building appraisal model, based on the surface defect feature data, the internal defect feature data, and the potential feature data of multiple building layers of the target building and the building component appraisal results, conduct safety appraisals on each of the building layers to obtain the building partial appraisal results; Using a preset building appraisal model, based on the surface defect feature data, the internal defect feature data, and the potential feature data corresponding to multiple key points of the target building respectively and the building layer appraisal results, conduct safety appraisals on the overall building to obtain the overall building appraisal results.

6. A computer device, characterized in that, It includes a processor and a memory. The memory is used to store a computer program. When the computer program is executed by the processor, it implements the dangerous and old building safety appraisal method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, It stores a computer program. When the computer program is executed by a processor, it implements the dangerous and old building safety appraisal method according to any one of claims 1 to 4.

Images