A smart city building deformation monitoring internet of things large model system and method

Abstract

The application provides a smart city building deformation monitoring Internet of Things large model system and method, which is executed based on a government supervision and management platform and comprises the following steps: determining equipment distribution parameters based on three-dimensional data of a target building; generating deployment instructions based on the equipment distribution parameters, and controlling a robot to install a plurality of monitoring devices based on the deployment instructions; determining deformation data of the target building in a second time period through a deformation prediction model based on monitoring data obtained from the plurality of monitoring devices in a first time period; determining a plurality of control forces based on the deformation data, and determining first protection parameters based on the plurality of control forces; and sending control signals to a damper network based on the first protection parameters, so that the servo motor actuators of each damper unit of the damper network generate a force. The city building is supervised by using the Internet of Things large model system, the deformation of the city building can be monitored and quickly responded, and the safety and reliability of the city building are effectively improved.

Description

Technical Field

[0001] This specification relates to the field of building monitoring technology, and in particular to a smart city building deformation monitoring IoT large-scale model system and method. Background Technology

[0002] In recent years, with the acceleration of urbanization, the safety and stability of buildings have increasingly attracted people's attention. During use, buildings may deform due to natural factors (such as earthquakes and rainstorms) or human factors (such as construction vibrations and load changes), which can even lead to structural failure in severe cases. Currently, building monitoring technology usually only sets up a small number of observation points manually in important parts of the building, which is difficult to comprehensively reflect the deformation of all areas of the building, especially in areas without monitoring points, where deformation may be missed. In addition, when a building deforms, the system cannot promptly assess the risk of loss based on the deformation data, nor can it activate corresponding emergency measures.

[0003] Therefore, it is hoped that a smart city building deformation monitoring IoT large-scale model system and method can be proposed to address the shortcomings of current monitoring technologies, achieve comprehensive and real-time monitoring of buildings, and improve the effectiveness and timeliness of building safety management. Summary of the Invention

[0004] This specification provides one or more embodiments of a smart city building deformation monitoring IoT large-scale model system. The system includes a government supervision and management platform, a government supervision sensor network platform, and a government supervision perception and control platform. The government supervision perception and control platform includes monitoring equipment. The government supervision and management platform is configured to: determine equipment distribution parameters based on three-dimensional data of a target building; generate deployment instructions based on the equipment distribution parameters, and control a robot to install multiple monitoring devices based on the deployment instructions; determine deformation data of the target building in a second time period based on monitoring data obtained from the multiple monitoring devices within a first time period, using a deformation prediction model; the deformation prediction model is a machine learning model; the deformation data includes deformation amplitude, deformation location, and deformation direction; determine multiple control forces based on the deformation data, and determine a first protection parameter based on the multiple control forces; and send control signals to a damper network based on the first protection parameter to drive the servo motor actuators of each damper unit in the damper network to generate force.

[0005] This specification provides one or more embodiments of a smart city building deformation monitoring method. The method is executed on a government regulatory management platform based on a smart city building deformation monitoring IoT large-scale model system. The method includes: determining device distribution parameters based on three-dimensional data of the target building; generating deployment instructions based on the device distribution parameters, and controlling a robot to install multiple monitoring devices based on the deployment instructions; determining deformation data of the target building in a second time period based on monitoring data obtained from the multiple monitoring devices within a first time period, using a deformation prediction model; the deformation prediction model is a machine learning model; the deformation data includes deformation amplitude, deformation location, and deformation direction; determining multiple control forces based on the deformation data, and determining a first protection parameter based on the multiple control forces; and sending control signals to a damper network based on the first protection parameter to drive the servo motor actuators of each damper unit in the damper network to generate force.

[0006] The beneficial effects that some embodiments of this specification may bring include, but are not limited to: 1) By determining multiple control forces, the damping adjustment value of the damper unit can be determined, and the force generated by adjusting the damping of the damper unit can be transmitted to the main steel structure of the target building through the damper unit and the anchor base. This force can counteract the deformation trend of the target building and prevent the target building from becoming a dangerous building, thereby protecting the target building. 2) By dividing the target building and its environmental area within a preset range into multiple nodes (first-type nodes and second-type nodes), and connecting the sub-regions and environmental areas with second-type edges, monitoring the environmental data of the environmental areas adjacent to the sub-regions, and considering the impact of the environmental areas on the target building, the target building can be assessed more comprehensively and meticulously, thereby better protecting the target building. 3) By dividing the target building into multiple sub-regions, constructing a building map based on the deformation data of the first time period within the multiple sub-regions, and further determining the deformation data of the sub-regions within the second time period based on the building map, the deformation data of the target building within the second time period can be determined more accurately, thereby better assessing the deformation of the target building and facilitating the subsequent adoption of better protective measures to protect the target building. 4) By determining risk losses through deformation data and dynamically adjusting drainage system parameters (slope, pump power) based on both risk loss and deformation magnitude, precise risk response can be achieved, improving structural safety while optimizing energy efficiency. A tiered protection mechanism avoids excessive intervention in non-critical areas, reducing equipment wear and enhancing the system's adaptability under complex conditions. 5) By establishing a dynamic risk-based prevention and control system, when both risk loss and structural deformation exceed limits, the system can accurately locate high-risk areas and automatically trigger gas valve closure, upgrading from passive monitoring to proactive intervention. Furthermore, the dual triggering of risk loss and deformation magnitude prevents energy waste or operational interruptions caused by false triggering, thereby improving the accuracy of prevention and control. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is an exemplary structural diagram of a smart city building deformation monitoring IoT large model system according to some embodiments of this specification;

[0009] Figure 2 This is an exemplary flowchart of a smart city building deformation monitoring method according to some embodiments of this specification;

[0010] Figure 3This is an exemplary schematic diagram of a modified data determination method according to some embodiments of this specification;

[0011] Figure 4 This is another exemplary flowchart of a smart city building deformation monitoring method according to some embodiments of this specification. Detailed Implementation

[0012] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0013] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0014] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0016] Figure 1 This is an exemplary structural diagram of a smart city building deformation monitoring IoT large model system according to some embodiments of this specification.

[0017] In some embodiments, such as Figure 1 As shown, the smart city building deformation monitoring IoT large model system (hereinafter referred to as the system) 100 may include a government supervision and management platform 110, a government supervision sensor network platform 120, and a government supervision perception and control platform 130.

[0018] It is worth noting that the platforms can communicate with each other, and each platform may include its own processor and memory, or it may share the same processor and memory.

[0019] A government regulatory management platform refers to a platform used by the government to regulate or manage information related to urban buildings. In some embodiments, the government regulatory management platform is configured to: determine equipment distribution parameters based on three-dimensional data of the target building; generate deployment instructions based on the equipment distribution parameters, and control a robot to install multiple monitoring devices based on the deployment instructions; determine deformation data of the target building in a second time period based on monitoring data obtained from the multiple monitoring devices within a first time period, using a deformation prediction model; determine multiple control forces based on the deformation data, and determine a first protection parameter based on the multiple control forces; and send control signals to a damper network based on the first protection parameter to drive the servo motor actuators of each damper unit in the damper network to generate force.

[0020] A government regulatory sensor network platform refers to a platform used by the government for the comprehensive management of sensor information. In some embodiments, the government regulatory sensor network platform can interact with a government regulatory management platform and a government regulatory perception and control platform.

[0021] A government regulatory sensing and control platform refers to a platform used by the government to collect data and / or information. In some embodiments, the government regulatory sensing and control platform includes monitoring equipment. Monitoring equipment refers to equipment used to monitor the main factors that directly act on the target building and cause deformation of the target building. For example, light sensors, rain gauges, etc. In some embodiments, the government regulatory sensing and control platform also includes dampers, drainage pumps, gas valves, etc.

[0022] For more information on the IoT-based large-scale model system for monitoring building deformation in smart cities, please refer to [link / reference]. Figures 2-4 And its related descriptions.

[0023] In some embodiments of this specification, the use of an IoT large-scale model system to monitor urban buildings enables the monitoring and rapid response to building deformation. By intelligently analyzing monitoring data to determine deformation data and implementing intelligent protection, potential safety hazards can be eliminated in a timely manner, effectively improving the safety and reliability of urban buildings. Simultaneously, the integration of automated control and operation reduces manpower and lowers management costs.

[0024] Figure 2 This is an exemplary flowchart illustrating a smart city building deformation monitoring method according to some embodiments of this specification. Figure 2 As shown, process 200 includes steps 210-250. In some embodiments, process 200 can be executed by the government regulatory management platform of the smart city building deformation monitoring IoT big data model system.

[0025] Step 210: Determine the equipment distribution parameters based on the three-dimensional data of the target building.

[0026] A target building refers to an object with a three-dimensional structure that is subject to deformation monitoring. For example, target buildings include houses (such as residences, factories, etc.) and historical buildings.

[0027] The three-dimensional data of a target building refers to data used to characterize the target building's location and form (or three-dimensional structure) in three-dimensional space. In some embodiments, the three-dimensional data includes a three-dimensional model. In some embodiments, the three-dimensional data of the target building can be obtained from third-party platforms (such as housing management bureaus, natural resources and planning bureaus, etc.).

[0028] Equipment distribution parameters refer to parameters used to characterize the installation locations of multiple monitoring devices. For example, equipment distribution parameters may include the top of a target building, the ground, a side wall, or a specific location. For more information on monitoring devices, please refer to [link to relevant documentation]. Figure 1 And its related descriptions.

[0029] The government monitoring and management platform can determine equipment distribution parameters based on the 3D data of the target building through various methods. In some embodiments, the platform can determine the locations within the target building that meet preset conditions as equipment distribution parameters based on the building's 3D data. These preset conditions may include the presence of a hazard (e.g., missing building materials, minor cracks, etc.) or the time elapsed since the last maintenance exceeding a preset time threshold. The preset time threshold can be manually set.

[0030] Step 220: Based on the device distribution parameters, generate deployment instructions, and control the robot to install multiple monitoring devices based on the deployment instructions.

[0031] A deployment instruction is a directive or instruction used to control a robot to install multiple monitoring devices. In some embodiments, the deployment instruction includes the robot's movement path and stopping position. The movement path may refer to the path the robot takes from its current location to the installation location of the monitoring devices. The stopping position can be understood as the location where the robot installs the monitoring devices, i.e., the installation location of the monitoring devices. In some embodiments, the deployment instruction also includes the installation steps for the monitoring devices.

[0032] It is understandable that multiple monitoring devices can be of the same or different types. For monitoring devices of the same type, the installation steps can be the same, but the installation locations can be different. For monitoring devices of different types, the installation steps can be different, but the installation locations can be the same or different (such as installing multiple different monitoring devices in the same location).

[0033] The government monitoring and management platform can generate deployment instructions in various ways based on device distribution parameters. In some embodiments, the platform can generate deployment instructions based on device distribution parameters and the robot's current location through a preset program. This preset program can be manually pre-programmed.

[0034] The robot may include an autonomous mobile robot. For example, the robot can install multiple monitoring devices according to deployment instructions. In some embodiments, a government regulatory management platform can communicate with the robot. In response to receiving deployment instructions from the government regulatory management platform, the robot can install multiple monitoring devices based on the deployment instructions.

[0035] Step 230: Based on the monitoring data obtained from multiple monitoring devices during the first time period, the deformation data of the target building during the second time period is determined using a deformation prediction model.

[0036] The first time period refers to a period of time that has already occurred. For example, the first time period includes the past week, the past month, etc.

[0037] Monitoring data refers to relevant data acquired by monitoring equipment. In some embodiments, monitoring data includes sunshine duration and rainfall. In some embodiments, a government regulatory management platform can communicate with monitoring equipment to acquire monitoring data for a first time period from multiple monitoring devices.

[0038] The second time period refers to a future period of time. For example, the second time period may include next week or next month. It is worth noting that the duration of the second time period may be the same as or different from that of the first time period.

[0039] Deformation data refers to data reflecting changes in the structure, location, shape, etc., of a target building. In some embodiments, deformation data includes deformation amplitude, deformation location, and deformation direction. Deformation amplitude reflects the degree of deformation. For example, deformation amplitude may include displacement values, strain values, etc. Deformation location refers to the location where the target building deforms. For example, deformation location may include the location where cracks appear in the target building. Deformation direction refers to the direction in which the target building deforms, or the orientation of the deformation. For example, deformation direction may include the direction in which a beam in the target building tilts.

[0040] A deformation prediction model is a model that predicts the deformation data of a target building during a second time period. In some embodiments, the deformation prediction model is a machine learning model. For example, the deformation prediction model includes one or more combinations of deep neural network (DNN) models or other custom models.

[0041] In some embodiments, the input to the deformation prediction model can be monitoring data within a first time period, and the output of the deformation prediction model can be deformation data of the target building within a second time period.

[0042] In some embodiments, the deformation prediction model can be obtained by training an initial deformation prediction model using multiple sets of first training samples with a first label. The first training samples may include sample monitoring data within a first historical time period. The sample monitoring data may include sample illumination time and sample rainfall. The first label may include deformation data actually detected in the target building within a second historical time period under the first training samples. The first historical time period precedes the second historical time period, and the first historical time period has the same duration as the first time period, and the second historical time period has the same duration as the second time period.

[0043] In some embodiments, the first training sample and the first label may be obtained based on historical data.

[0044] In some embodiments, the government regulatory management platform can input multiple first training samples with a first label into an initial deformation prediction model. A loss function is constructed using the first label and the results of the initial deformation prediction model. Based on the loss function, the parameters of the initial deformation prediction model are iteratively updated using gradient descent or other methods. When preset conditions are met, model training is complete, resulting in a trained deformation prediction model. These preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0045] For further instructions on step 230, please refer to other parts of this manual (such as...). Figure 3 (and related descriptions).

[0046] Step 240: Based on the deformation data, determine multiple control forces, and based on the multiple control forces, determine the first protection parameter.

[0047] Control force refers to the force used to counteract the deformation data of the target building. For example, control force can include torque, axial force, shear force, etc. In some embodiments, control force can be implemented through individual damper units of a damper network. For example, the servo motor actuator of each damper unit can generate different forces by adjusting the damping of the corresponding damper unit, thereby forming multiple control forces. For more information on damper networks, damper units, and servo motor actuators, please refer to the relevant description in step 250.

[0048] In some embodiments, for each damper unit of the damper network, the government regulatory management platform can weight the deformation amplitude (e.g., strain value) at deformation locations within a preset distance range of the damper unit to generate a control urgency value. In response to the control urgency value exceeding a first preset threshold, the government regulatory management platform can initiate intervention in the damper network, executing step 250. The weighting weight can be inversely proportional to the distance between the deformation location and the damper unit. The preset distance range and the first preset threshold can be manually preset.

[0049] The government regulatory management platform can determine multiple control forces based on deformation data through various methods. In some embodiments, the platform can determine these forces by querying a first preset table. For example, based on the deformation location and direction in the deformation data, the platform can determine the type and magnitude of the control force applied at that deformation location by querying the first preset table. The first preset table can include multiple sets of correspondences between control forces and deformation data. In some embodiments, the first preset table can be constructed through simulation based on the deformation data. That is, through simulation, multiple control forces required to counteract specific deformation data for a target building can be obtained.

[0050] The first protection parameter refers to the parameter used to implement protective measures on the target building. In some embodiments, the first protection parameter may include a damping adjustment value. The damping adjustment value refers to the adjustment value applied to each damper element of the damper network.

[0051] The government regulatory management platform can determine the first protection parameter based on multiple control forces and through various methods. In some embodiments, the government regulatory management platform can determine the damping adjustment value by querying a second preset table. The second preset table can include the correspondence between multiple control forces and damping adjustment values. For example, the larger the control force, the larger its corresponding damping adjustment value. In some embodiments, the second preset table can be constructed through simulation based on multiple control forces.

[0052] Step 250: Based on the first protection parameters, a control signal is sent to the damper network to drive the servo motor actuators of each damper unit in the damper network to generate force.

[0053] A damper network refers to a network structure composed of multiple damper units working together. A damper network can include multiple damper units pre-deployed at different locations within a target building. A damper network can enhance the target building's resistance to interference through energy dissipation, vibration suppression, and dynamic regulation. For example, a damper network can disperse the vibration energy from earthquakes or strong winds, reducing the sway amplitude of the target building. Another example is that a damper network can convert seismic wave energy into heat energy, reducing the deformation of the target building. Yet another example is that a damper network can exert forces on the target building to weaken or counteract its deformation. In some embodiments, the damper network is communicatively connected to a government regulatory management platform.

[0054] Each damper unit may include a servo motor actuator. The servo motor actuator, in response to a received control signal, adjusts the damping of the corresponding damper unit based on a first protection parameter, thereby generating a force. This force is transmitted from the damper unit to an anchoring base connected to the damper unit, and ultimately acts on the main steel structure of the target building to form a control force, thereby counteracting the deformation of the target building. The force refers to the force acting on the main steel structure of the target building. For example, the force may include axial force, shear force, etc. The anchoring base may be pre-embedded in the target building.

[0055] A control signal is a signal used to coordinate and guide the individual damper units of a damper network to perform specific operations. In some embodiments, the control signal can be used to drive a servo motor actuator of a damper unit to adjust the damping of the damper unit based on a first protection parameter to generate a force.

[0056] In some embodiments, the government regulatory management platform can automatically send control signals to the damper network based on a first protection parameter. The servo motor actuators of each damper unit in the damper network can respond to the received control signal and adjust the damping of the corresponding damper unit based on the first protection parameter (e.g., a damping adjustment value), thereby generating different forces to counteract the deformation of the target building at different deformation locations.

[0057] In some embodiments of this specification, by determining multiple control forces, the damping adjustment value of the damper unit is determined, and the damping of the damper unit is adjusted to generate an action force. This action force is transmitted to the main steel structure of the target building through the damper unit and the anchoring base. This can counteract the monitored deformation trend of the target building and prevent the target building from becoming a dangerous building, thereby protecting the target building.

[0058] Figure 3 This is an exemplary schematic diagram of a modified data determination method according to some embodiments of this specification.

[0059] In some embodiments, such as Figure 3As shown, the government regulatory management platform can divide the target building 320 into multiple sub-regions (e.g., first sub-region 320-1, second sub-region 320-2, ..., Nth sub-region 320-N) based on the partitioning parameter 310; construct a building map 340 based on the monitoring data within the first time period within the multiple sub-regions (e.g., first monitoring data 330-1 corresponding to the first sub-region 320-1, second monitoring data 330-2 corresponding to the second sub-region 320-2, ..., and Nth monitoring data 330-N corresponding to the Nth sub-region 320-N); and determine the deformation data of the target building 320 within the second time period (e.g., first deformation data 360-1 corresponding to the first sub-region 320-1, second deformation data 360-2 corresponding to the second sub-region 320-2, ..., and Nth deformation data 360-N corresponding to the Nth sub-region 320-N) through the deformation prediction model 350 based on the building map 340.

[0060] Zoning parameters refer to the parameters used to divide a target building into zones. For example, zoning parameters may include the location and size of each sub-zone. A sub-zone refers to multiple zones resulting from the division of the target building. Figure 3 As shown, a target building 320 can be divided into N sub-regions, such as the first sub-region 320-1, the second sub-region 320-2, ..., and the Nth sub-region 320-N. Where N is an integer and not less than 2.

[0061] In some embodiments, partitioning parameters may be preset based on prior experience.

[0062] In some embodiments, the government regulatory management platform can acquire monitoring data within a first time period across multiple sub-regions using monitoring equipment. For details regarding monitoring equipment, the first time period, and monitoring data, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0063] A building map is a map that reflects relevant information about a target building (such as 3D data or monitoring data). For example, a building map can reflect information such as the amount of sunlight a target building receives and the amount of rainfall.

[0064] In some embodiments, the government regulatory management platform can construct a housing graph using nodes and edges. This is merely an example. Figure 3 As shown, the house graph 340 includes multiple nodes and multiple edges. Two nodes among the multiple nodes (e.g., P1 and P2) can be connected by an edge L.

[0065] A node refers to a target building and a portion of its preset area. For example, a node may include a sub-area of ​​the target building. Or, for example, a node may include a portion of the target building's preset area (e.g., an area covered by vegetation). The preset area can be manually preset. More information about preset areas can be found in the following description.

[0066] In some embodiments, the plurality of nodes may include a first type of node.

[0067] The first type of node is a sub-region. For example, a sub-region can be called a first-type node. In some embodiments, if there are multiple monitoring devices in a sub-region, the government regulatory management platform can further divide the area range (e.g., spatial size) that each monitoring device in the sub-region can monitor into a first-type node. For example, a sub-region with n (n is an integer not less than 2) monitoring devices can be further divided into n first-type nodes.

[0068] In some embodiments, the node characteristics of a first type of node include monitoring data within a first time period in multiple sub-regions and the spatial size of the multiple sub-regions. The spatial size of the multiple sub-regions can be determined based on partitioning parameters. If there are no monitoring devices within a first type of node, the monitoring data in the node characteristics of that first type of node is empty.

[0069] An edge is a boundary line between adjacent sub-regions or between an environmental region and its adjacent sub-regions. For example, ... Figure 3 As shown, there is an edge L between two sub-regions (also referred to as first-type nodes P). In some embodiments, first-type edges exist between adjacent sub-regions.

[0070] Type I edges are boundaries that connect adjacent sub-regions (also called Type I nodes). Type I edges can be determined based on the positions of adjacent sub-regions.

[0071] In some embodiments, the edge features of the first type of edge include the segmentation type of the two sub-regions connected by the edge. The segmentation type refers to the method used to segment the region. For example, the segmentation type may include segmentation based on building walls, segmentation based on the area that can be monitored by the monitoring device, or no segmentation. In some embodiments, the segmentation type may be determined based on the 3D data of the target building and the 3D structure of multiple sub-regions.

[0072] In some embodiments, the node characteristics of the first type of node also include the most recent maintenance time and corresponding maintenance type of multiple sub-regions, the three-dimensional structure of the multiple sub-regions, and the construction materials.

[0073] The most recent maintenance time refers to the time when the target building was last maintained. For example, the maintenance time could be within the past week or a few days in the past.

[0074] Maintenance type refers to the type of maintenance performed on the target building. For example, maintenance types may include wall repair, door and window repair, reinforcement, renovation, etc.

[0075] The three-dimensional structure of a subregion can be used to characterize the shape and size of the subregion in three-dimensional space. In some embodiments, the three-dimensional structure of the subregion can be characterized by a three-dimensional model or by data. For example, if the subregion is a cuboid, its three-dimensional structure can be characterized by the numerical values ​​of its length, width, and height.

[0076] Building materials refer to information about the materials used to construct a sub-region (e.g., material type, material quantity, etc.). For example, building materials may include bricks, wood, concrete, etc., and their corresponding quantities.

[0077] In some embodiments, the most recent maintenance time and corresponding maintenance type of multiple sub-regions, as well as the three-dimensional structure and construction materials of multiple sub-regions, can be obtained from third-party platforms (such as housing management bureaus, natural resources and planning bureaus) or can be obtained through manual input.

[0078] In some embodiments, environmental monitoring points in the environmental area of ​​the target building are equipped with environmental monitoring devices configured to acquire environmental data. The plurality of nodes also includes a second type of node covering environmental areas within a preset range of the target building; the node characteristics of the second type of node include the type of environmental area covered and the environmental data.

[0079] An environmental area refers to the environmental type of the area within the pre-defined scope of the target building. For example, an environmental area may include a vegetation-covered area, a concrete-covered area, a lake area, etc. An environmental monitoring point refers to a location used to monitor relevant information (such as environmental data) within the environmental area. For example, an environmental monitoring point may include the monitoring location of an environmental monitoring device. An environmental monitoring device refers to a device used to monitor environmental data within the environmental area. For example, an environmental monitoring device may include, but is not limited to, a thermometer or a hygrometer. Environmental data can reflect relevant information about the environmental area. For example, environmental data may include ambient temperature, ambient humidity, etc.

[0080] The second type of node refers to a portion of the target building within a preset range. In some embodiments, the second type of node may include an environmental area within the preset range of the target building.

[0081] In some embodiments, the preset range may include a range centered on the target building and within a preset distance threshold (e.g., 5m, 10m, etc.) from the target building.

[0082] In some embodiments, the type of environmental region covered in the node characteristics of the second type of node can be obtained from a third-party platform (such as the Natural Resources and Planning Bureau, map APP, etc.) or can be obtained by manual input.

[0083] In some embodiments, there is a second type of edge between the environmental region adjacent to the multiple sub-regions and the multiple sub-regions, and the edge characteristics of the second type of edge include the environmental adjacency factor.

[0084] The second type of edge refers to the boundary between the sub-region and the adjacent environmental region. In some embodiments, the second type of edge can be determined based on the sub-region and its adjacent environmental regions.

[0085] The environmental adjacency factor is a parameter used to measure the impact of an environmental area on a target building. For example, if an environmental area has no impact on the target building, the environmental adjacency factor is 0. Conversely, the greater the impact of the environmental area on the target building, the greater the environmental adjacency factor. In some embodiments, the environmental adjacency factor can be determined empirically.

[0086] Some embodiments of this specification divide the target building and its environmental area within a preset range into multiple nodes (first type nodes and second type nodes), connect the sub-regions and the environmental area with second type edges, monitor the environmental data of the environmental area adjacent to the sub-regions, and consider the impact of the environmental area on the target building. This allows for a more comprehensive and detailed assessment of the target building, thus better protecting it.

[0087] In some embodiments, the input to the deformation prediction model may be a building map, and the output of the deformation prediction model may be deformation data of multiple sub-regions of the target building within a second time period.

[0088] In some embodiments, the deformation prediction model can also be obtained by training the initial deformation prediction model using multiple sets of second training samples with second labels. In some embodiments, the second training samples may include sample building maps, and the second labels may include deformation data of multiple sub-regions of the target building actually detected within a second historical time period under the second training samples. The second historical time period is located after the first historical time period. For further explanation of the first and second historical time periods, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0089] In some embodiments, the second training sample and the second label may be obtained based on historical data.

[0090] It should be noted that this deformation prediction model (which can be called the second deformation prediction model) and its training method are similar to the aforementioned deformation prediction model (which can be called the first deformation prediction model) and its training method. For details, please refer to [link to relevant documentation]. Figure 2The relevant description of step 230.

[0091] In some embodiments of this specification, by dividing the target building into multiple sub-regions, constructing a building atlas based on deformation data within a first time period in the multiple sub-regions, and further determining the deformation data of the sub-regions within a second time period based on the building atlas, the deformation data of the target building within the second time period can be determined more accurately, so as to better assess the deformation of the target building and thus facilitate the adoption of better protective measures to protect the target building.

[0092] Figure 4 This is an exemplary flowchart of a smart city building deformation monitoring method according to other embodiments of this specification. Figure 4 As shown, process 400 includes steps 410-430. In some embodiments, process 400 may be executed by a government regulatory management platform.

[0093] Step 410: Determine the risk loss based on the deformation data.

[0094] For more information on deformation data, please refer to Figure 2 The relevant description of step 230.

[0095] In some embodiments, the deformation data also includes deformation type. Deformation type refers to the type of morphological change of the building. For example, deformation type may include warping and bending caused by wet expansion and contraction, cracks and structural deformation caused by thermal expansion and contraction, and localized corrosion caused by biological invasion.

[0096] In some embodiments, deformation types can be obtained in various ways. For example, a government regulatory management platform can periodically capture images of the target building using surveillance cameras or drones, and analyze the deformation of the target building using image processing technology to obtain the deformation type. Alternatively, the deformation type can be obtained through manual on-site inspection and monitoring.

[0097] Risk loss can be used to measure the degree of danger posed by deformation of a target building. For example, the higher the risk loss value, the greater the danger posed by the deformation of the target building.

[0098] In some embodiments, the government regulatory management platform can determine the deformation amplitude threshold by querying a third preset table based on the deformation location and deformation type, thereby determining the risk loss. The third preset table may include multiple sets of correspondences between deformation locations, deformation types, and deformation amplitude thresholds. For example, for deformation locations and deformation types that have a greater impact on the target building (e.g., deformation location is a beam or other main structure; deformation type is cracks and structural deformation caused by thermal expansion and contraction), the corresponding deformation amplitude threshold is smaller. In some embodiments, the third preset table may be preset based on prior experience.

[0099] The deformation amplitude threshold refers to the maximum allowable deformation value set for different deformation locations and deformation types of the target building. In some embodiments, risk loss is negatively correlated with the deformation amplitude threshold. For example, the smaller the deformation amplitude threshold, the greater the risk loss.

[0100] Step 420: In response to the risk loss exceeding the loss threshold, for deformation locations where the deformation amplitude is less than the deformation threshold, a second protection parameter is determined based on the deformation data.

[0101] The loss threshold refers to the maximum level of loss that a target building can withstand. In some embodiments, the loss threshold can be obtained based on prior experience.

[0102] The deformation threshold refers to the maximum deformation value that the target building can improve under the first protective measure. In some embodiments, the deformation threshold may be preset based on prior experience. For more information on the first protective measure, please refer to the relevant description of step 430.

[0103] The second protection parameter refers to the technical specifications and equipment parameters set by the system to reduce damage to the target building caused by external environmental factors. In some embodiments, the second protection parameter may include the slope of the drainage system, the activated drainage pump, and the corresponding power.

[0104] The government regulatory management platform can determine the second protection parameter based on deformation data through various methods. In some embodiments, the platform can determine the second protection parameter by querying a fourth preset table based on the deformation data. For example, when the deformation type is warping and bending caused by wet expansion and contraction, it is determined that there is water blistering (or other liquids). Based on the deformation location, deformation type, and deformation amplitude, the platform determines the slope of the drainage system, the activated drainage pump, and its power by querying the fourth preset table. The fourth preset table can be used to characterize the correspondence between the deformation data and the second protection parameter. In some embodiments, the fourth preset table can be determined based on prior experience.

[0105] Step 430: Based on the second protection parameters, implement the first protection measure.

[0106] The first protective measure refers to the specific protective measures that dynamically adjust the equipment's operating parameters based on the second protective parameter. For example, activating a water pump to drain water and reduce pressure or activating a damper.

[0107] In some embodiments, the government regulatory management platform can implement the first protection measure in a variety of ways. For example, it can use an intelligent control algorithm to adjust the slope based on the slope of the drainage system in the second protection parameter.

[0108] In some embodiments, the government regulatory management platform performs a first protective measure based on a second protective parameter, including: rotating the water pipe at the drain outlet based on the slope of the drainage system; and / or controlling the activated drainage pump to operate based on a corresponding power.

[0109] For example, the government regulatory management platform can adjust the slope of the drainage system using adjustable connectors, slope monitoring instruments, and electric adjustment devices. For instance, the slope monitoring instrument detects the slope of the water pipe at the current drainage outlet. If the slope of the drainage outlet does not meet the drainage system slope requirements in the second protection parameter, the government regulatory management platform will automatically send an adjustment signal to the electric adjustment device of the adjustable connector, which will then rotate the water pipe to the required slope.

[0110] For example, a government regulatory platform can monitor the operating parameters (such as power) of drainage pumps in real time using a comprehensive pump tester. If the operating parameters of a drainage pump do not meet the power requirements of the activated drainage pump in the second protection parameter, an adjustment signal is automatically sent to the drainage pump control system. Upon receiving the adjustment signal, the drainage pump control system adjusts the operating parameters of the corresponding drainage pump to achieve the required power.

[0111] In some embodiments of this specification, by determining risk loss through deformation data and dynamically adjusting drainage system parameters (slope, pump power) based on the dual determination of risk loss and deformation amplitude, accurate risk response can be achieved, improving structural safety while optimizing energy utilization efficiency; by using a graded protection mechanism to avoid excessive intervention in non-critical areas, equipment wear can be reduced and the system's adaptability under complex working conditions can be improved.

[0112] In some embodiments, the smart city building deformation monitoring method further includes: in response to a risk loss exceeding a loss threshold, determining a third protection parameter based on deformation data for deformation locations where the deformation amplitude is greater than the deformation threshold; and performing a second protection measure based on the third protection parameter, including: controlling the gas valve at a preset location to close based on a gas interruption command.

[0113] For more information on risk loss, loss threshold, deformation range, and deformation threshold, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0114] The third protection parameter refers to an emergency parameter used when the system's risk loss exceeds a loss threshold and the deformation amplitude is greater than a deformation threshold. It is used to cut off the source of danger and reduce secondary damage. Examples include whole-house power outage commands and water outage commands. In some embodiments, the third protection parameter includes a gas interruption command.

[0115] In some embodiments, in response to a risk loss exceeding a loss threshold, for deformation locations where the deformation amplitude is greater than the deformation threshold, the government regulatory management platform can automatically generate third protection parameters based on deformation data through a preset program. The preset program can be manually preset.

[0116] The second protective measure refers to the specific protective measures implemented based on the third protective parameter. For example, turning off the main power switch or shutting off the gas valve.

[0117] A gas interruption command is a command used to control the interruption or closure of gas equipment / valves. For example, a gas interruption command may include gas equipment that needs to be interrupted, gas valves that need to be closed, etc.

[0118] In some embodiments, the government regulatory management platform can implement secondary protection measures in various ways based on third protection parameters. For example, threshold triggering, tiered decision-making, and anomaly feedback.

[0119] In some embodiments, the government regulatory management platform can send a gas interruption command to a gas valve at a preset location based on a gas interruption command, thereby controlling the gas valve at the preset location to close. The preset location can be manually determined. For example, the preset location could be the location of a gas valve within a sub-region where the deformation amplitude exceeds a deformation threshold when the risk loss exceeds that threshold. The gas valve could be a solenoid valve, etc.

[0120] In some embodiments of this specification, by establishing a dynamic prevention and control system based on risk classification, when both risk loss and structural deformation exceed limits, the system can accurately locate high-risk areas and automatically trigger the gas valve to close, achieving an upgrade from passive monitoring to proactive intervention. Furthermore, the dual-condition triggering of risk loss and deformation magnitude can avoid energy waste or operational interruptions caused by false triggering, thereby improving the accuracy of prevention and control.

[0121] It should be noted that the above descriptions of processes 200 and 400 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to processes 200 and 400 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0122] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

Claims

1. A smart city building deformation monitoring IoT large-scale model system, characterized in that, The system includes a government regulatory management platform, a government regulatory sensor network platform, and a government regulatory perception and control platform; the government regulatory perception and control platform includes monitoring equipment, and the government regulatory management platform is configured as follows: Based on the 3D data of the target building, determine the equipment distribution parameters; Based on the device distribution parameters, a deployment instruction is generated, and based on the deployment instruction, a robot is controlled to install multiple monitoring devices; Based on monitoring data acquired from multiple monitoring devices over a first time period, deformation data of the target building over a second time period is determined using a deformation prediction model. The deformation prediction model is a machine learning model. The deformation data includes deformation amplitude, deformation location, deformation type, and deformation direction. The monitoring data includes sunshine duration and rainfall, including: Based on the partitioning parameters, the target building is divided into multiple sub-regions; Based on the monitoring data within the first time period in the multiple sub-regions, a house map is constructed; Based on the building atlas, the deformation prediction model determines the deformation data of the target building in multiple sub-regions within the second time period. The building atlas includes multiple nodes and multiple edges. The multiple nodes include a first type of node, which represents the multiple sub-regions. Adjacent sub-regions are connected by first type edges. The node features of the first type of node include the monitoring data within the multiple sub-regions during the first time period and the spatial size of the multiple sub-regions. The edge features of the first type of edge include the segmentation type of the two sub-regions connected by the edge. The segmentation type is determined based on the three-dimensional data of the target building and the three-dimensional structure of the multiple sub-regions. The node characteristics of the first type of node also include the most recent maintenance time and corresponding maintenance type of the multiple sub-regions, the three-dimensional structure of the multiple sub-regions, and the construction materials; The environmental monitoring points in the environmental area of ​​the target building are equipped with environmental monitoring devices, which are configured to acquire environmental data. The plurality of nodes also includes a second type of node in the environmental area within a preset range of the target building; the node characteristics of the second type of node include the type of coverage of the environmental area and the environmental data; A second type of edge exists between the environmental region adjacent to the plurality of sub-regions and the plurality of sub-regions, and the edge characteristics of the second type of edge include an environmental adjacency factor; Based on the deformation data, multiple control forces are determined, and a first protection parameter is determined based on the multiple control forces; Based on the first protection parameters, control signals are sent to the damper network to drive the servo motor actuators of each damper unit in the damper network to generate force; and, Based on the deformation data, the risk loss is determined; In response to the risk loss exceeding a loss threshold, for the deformation location where the deformation amplitude is less than the deformation threshold, a second protection parameter is determined based on the deformation data; the second protection parameter includes the slope of the drainage system, the activated drainage pump, and the corresponding power. Based on the second protection parameter, the first protection measure is implemented, including: rotating the water pipe of the drain outlet based on the slope of the drainage system, and / or controlling the activated drainage pump to operate based on the power. In response to the risk loss exceeding the loss threshold, for the deformation location where the deformation amplitude is greater than the deformation threshold, a third protection parameter is determined based on the deformation data; the third protection parameter includes a gas interruption command; Based on the third protection parameter, the second protection measure is executed, including: based on the gas interruption command, controlling the gas valve at a preset position to close.

2. A method for monitoring building deformation in smart cities, characterized in that, The method is implemented based on the government supervision and management platform of the smart city building deformation monitoring IoT big data model system, and the method includes: Based on the 3D data of the target building, determine the equipment distribution parameters; Based on the device distribution parameters, a deployment instruction is generated, and based on the deployment instruction, the robot is controlled to install multiple monitoring devices. Based on monitoring data acquired from the multiple monitoring devices during a first time period, deformation data of the target building during a second time period is determined using a deformation prediction model. The deformation prediction model is a machine learning model. The deformation data includes deformation amplitude, deformation location, deformation type, and deformation direction. The monitoring data includes sunshine duration and rainfall, including: Based on the partitioning parameters, the target building is divided into multiple sub-regions; Based on the monitoring data within the first time period in the multiple sub-regions, a house map is constructed; Based on the building atlas, the deformation prediction model determines the deformation data of the target building in multiple sub-regions within the second time period. The building atlas includes multiple nodes and multiple edges. The multiple nodes include a first type of node, which represents the multiple sub-regions. Adjacent sub-regions are connected by first type edges. The node features of the first type of node include the monitoring data within the multiple sub-regions during the first time period and the spatial size of the multiple sub-regions. The edge features of the first type of edge include the segmentation type of the two sub-regions connected by the edge. The segmentation type is determined based on the three-dimensional data of the target building and the three-dimensional structure of the multiple sub-regions. The node characteristics of the first type of node also include the most recent maintenance time and corresponding maintenance type of the multiple sub-regions, the three-dimensional structure of the multiple sub-regions, and the construction materials; The environmental monitoring points in the environmental area of ​​the target building are equipped with environmental monitoring devices, which are configured to acquire environmental data. The plurality of nodes also includes a second type of node in the environmental area within a preset range of the target building; the node characteristics of the second type of node include the type of coverage of the environmental area and the environmental data; A second type of edge exists between the environmental region adjacent to the plurality of sub-regions and the plurality of sub-regions, and the edge characteristics of the second type of edge include an environmental adjacency factor; Based on the deformation data, multiple control forces are determined, and a first protection parameter is determined based on the multiple control forces; Based on the first protection parameters, control signals are sent to the damper network to drive the servo motor actuators of each damper unit in the damper network to generate force; and, Based on the deformation data, the risk loss is determined; In response to the risk loss exceeding a loss threshold, for the deformation location where the deformation amplitude is less than the deformation threshold, a second protection parameter is determined based on the deformation data; the second protection parameter includes the slope of the drainage system, the activated drainage pump, and the corresponding power. Based on the second protection parameter, the first protection measure is implemented, including: rotating the water pipe of the drain outlet based on the slope of the drainage system, and / or controlling the activated drainage pump to operate based on the power. In response to the risk loss exceeding the loss threshold, for the deformation location where the deformation amplitude is greater than the deformation threshold, a third protection parameter is determined based on the deformation data; the third protection parameter includes a gas interruption command; Based on the third protection parameter, the second protection measure is executed, including: based on the gas interruption command, controlling the gas valve at a preset position to close.

Images