A house settlement detection system and method based on intelligent sensing

Abstract

This invention proposes a building settlement detection system and method based on intelligent sensing. The method includes: acquiring and preprocessing structural response data and geological disturbance data from intelligent sensors to construct structural response data sets and geological disturbance data sets; collecting and measuring the coordinates of structural nodes and geological nodes of the actual building, and generating disturbance sensing vectors for the structural nodes by combining the structural response data sets and geological disturbance data sets; determining a propagation probability matrix based on the disturbance sensing vectors and a structural connection diagram, inferring the propagation path and intensity of settlement between structural nodes based on the propagation probability matrix, and generating a structural settlement propagation map with directional edges and weights; and determining and classifying risk scores based on the structural settlement propagation map, the current response state of the structural nodes, and the disturbance sensing vectors of the structural nodes, and triggering corresponding alarms. This invention is applicable to long-term intelligent settlement monitoring in the renovation of old buildings, construction in complex geological conditions, and the operation of high-rise buildings in cities.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of house settlement detection, and particularly relates to a house settlement detection system and method based on intelligent sensing. BACKGROUND

[0002] House structures are affected by many factors in the running process, such as uneven settlement of the foundation, fluctuation of the underground water level, and disturbance of surrounding construction, and are prone to structural deformation or even local instability, especially in high-rise buildings, old house reinforcement projects and complex geological areas. The traditional settlement monitoring method mainly uses manual leveling measurement and periodic point data collection, relies on manual re-measurement and historical comparison to judge the change trend, and is low in efficiency and poor in timeliness, and cannot capture small or sudden response changes. In recent years, automatic sensing monitoring means such as settlement meters and inclinometers have been gradually introduced, but most of these systems still focus on the state perception of the structure itself, and cannot effectively introduce the modeling capability of the disturbance source, so that the cause of abnormal response cannot be accurately located.

[0003] In addition, the existing method generally uses a simple threshold or time sequence fitting strategy, lacks modeling support for structural topology information, disturbance diffusion path and response evolution mechanism, and cannot realize explainable reasoning and propagation level warning of the settlement process. Especially in the engineering site with limited layout density and complex and variable disturbance sources, the current technology has exposed the short board in cross-modal correlation, abnormal conduction modeling and response linkage, which restricts the improvement of the settlement warning system from perception to intelligent identification and linkage response. SUMMARY

[0004] The purpose of the present application is to provide a house settlement detection system and method based on intelligent sensing, which has higher explainability and response robustness in the case of limited sensing density, complex disturbance path or slight response, and is suitable for long-term intelligent settlement monitoring of old building reconstruction, complex geological construction and urban high-rise operation.

[0005] In order to achieve the above purpose, in the first aspect of the present application, a house settlement detection method based on intelligent sensing is provided, which comprises the following steps:

[0006] S1, acquiring structure response data and geological disturbance data of intelligent sensors and preprocessing to construct a structure response data set and a geological disturbance data set; wherein the intelligent sensors include an inclinometer, a linear displacement sensor, a resistance strain gauge, a vibrating wire pore water pressure sensor and a three-component microseismic detector;

[0007] S2. Collect the structural node coordinates and geological node coordinates of the actual measured building, and combine them with the structural response data set and geological disturbance data set to generate disturbance perception vectors of the structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response status of several structural nodes;

[0008] S3. Determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram. Based on the propagation probability matrix, infer the propagation path and intensity of settlement between structural nodes, and generate a structural settlement propagation map with directional edges and weights, as well as a propagation determination matrix.

[0009] S4. Based on the structural settlement propagation map, the current response status of the structural nodes, and the disturbance perception vector of the structural nodes, determine the risk score and classify it, and trigger the corresponding alarm and control actions.

[0010] Furthermore, the structural response data includes the tilt angle value of the structural measuring point at time t, the vertical displacement of the structural measuring point, and the strain value of the structural measuring point; the geological disturbance data includes the pore pressure value of the geological disturbance measuring point and the main amplitude value of the microseismic wave at the geological disturbance measuring point.

[0011] The preprocessing includes:

[0012] For the main amplitude value of the micro-seismic wave, the maximum amplitude is extracted within each 1-second window as the main amplitude value at the current time point;

[0013] For the strain values ​​at the measuring points of the structure, a weighted average is used to obtain the standard value;

[0014] If a sensor has no data at the main time point t, linear interpolation or the nearest neighbor approximation value is used to ensure that the structural response data set and the geological disturbance data set correspond to the same time, so as to form a unified synchronous snapshot.

[0015] Furthermore, the preprocessing also includes: introducing a response differential mechanism into the structural response data and geological disturbance data, thereby enhancing the system's ability to identify minor subsidence by combining the response changes of the current smart sensors within the time window τ.

[0016] Furthermore, S2 specifically includes:

[0017] Calculate the three-dimensional Euclidean distance of any disturbance source point, and combine it with the current response state of the structural nodes to calculate the initial influence weight of the current disturbance point on the structural nodes;

[0018] A trainable spatial attention mechanism is introduced to calculate weighted coefficients by combining perturbation features and structural location; the perturbation features are obtained by standardizing the geological perturbation data.

[0019] By combining the initial influence weight, weighted action coefficient, and structural local response difference regularization term, the disturbance perception vector received by each structural node is calculated; wherein, the structural local response difference regularization term is calculated based on the current response state of the structural node and its adjacent structural nodes.

[0020] Furthermore, the trainable spatial attention mechanism is a multilayer perceptron, and the input is a concatenation of perturbation features and the relative spatial positions of perturbation points and structural points.

[0021] Furthermore, S3 specifically includes:

[0022] Calculate the similarity of the states of structural nodes;

[0023] It is determined that the current propagation only occurs between node pairs that are structurally connected.

[0024] Calculate the tilt angle value based on the current response state of the structural node;

[0025] The propagation probability matrix is ​​calculated by combining the structural node state similarity, judgment results, and tilt angle values, representing the intensity of the settlement impact transmission from the current node to the adjacent node at time t;

[0026] If the propagation probability matrix is ​​determined to be greater than a preset threshold, then it is considered that there is an effective subsidence propagation path from the current node to the adjacent node.

[0027] The resulting effective settlement propagation paths and propagation probability matrices construct a structural settlement propagation map; wherein, the node states of the structural settlement propagation map represent the current response states of the structural nodes.

[0028] Furthermore, the S4 specifically includes:

[0029] Extract all propagation paths from the aforementioned structural settlement propagation map, wherein each path consists of several structural nodes;

[0030] A weighted distance metric function that measures the difference between the current response state of the structural node and the perturbation sensing vector of the structural node;

[0031] Calculate the cumulative intensity of incoming path risk obtained from the propagation graph;

[0032] For each node in the path, the response risk score of the structural node is calculated by combining the weighted distance metric function, the cumulative strength of the incoming path risk, and the physical criticality weight.

[0033] The response risk score is mapped to the corresponding response level.

[0034] The structural nodes are mapped to the response linkage table according to the response level, so as to execute the corresponding linkage response.

[0035] Furthermore, the corresponding response level is 0-3, with a higher level indicating a more severe response.

[0036] Furthermore, the corresponding linkage response includes issuing an alarm, activating the foundation grouting module, blocking the passage structure push, notifying the engineering team to arrive on site, enabling enhanced monitoring, recording and marking key observation points in the system, prompting on-duty personnel to pay attention, and only saving the status without triggering a response.

[0037] In a second aspect, the present invention provides a building settlement detection system based on intelligent sensing, the system comprising:

[0038] Data acquisition subsystem: used to acquire and preprocess structural response data and geological disturbance data from intelligent sensors to construct structural response datasets and geological disturbance datasets; wherein the intelligent sensors include tilt sensors, linear displacement sensors, resistance strain gauges, vibrating wire pore water pressure sensors, and three-component microseismic detectors;

[0039] Coupled modeling subsystem: used to collect the coordinates of structural nodes and geological nodes of the actual measured building, and combine the structural response data set and the geological disturbance data set to generate disturbance perception vectors of structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response state of several structural nodes;

[0040] Path reasoning subsystem: used to determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram, reason the propagation path and intensity of settlement between structural nodes based on the propagation probability matrix, generate a structural settlement propagation map with directional edges and weights, and a propagation determination matrix;

[0041] Risk Response Subsystem: This system combines the structural settlement propagation map, the current response status of structural nodes, and the disturbance perception vector of structural nodes to determine and classify risk scores, and trigger corresponding alarms and control actions.

[0042] The beneficial technical effects of the present invention are at least as follows:

[0043] This invention not only integrates multimodal sensor inputs of structural response and geological disturbance, but also constructs a complete disturbance-response-propagation-response chain through a series of innovative modeling and reasoning mechanisms.

[0044] At the data level, the system constructs a synchronized set of structural response data and geological disturbance data by uniformly time-synchronizing and aligning the sampling frequency differences of heterogeneous sensors, and introduces a structural differential enhancement mechanism to enhance the ability to identify minor settlements.

[0045] At the modeling level, the system constructs a disturbance propagation graph model that integrates spatial perception and physical attenuation mechanisms based on structural nodes and disturbance nodes. It innovatively designs a causal modeling network of disturbance-structural response to make the influence mechanism of geological disturbance on structural changes explicit.

[0046] At the reasoning level, based on the structural connection graph, a settlement path reasoning mechanism is proposed that incorporates state similarity, propagation direction consistency and structural topological constraints to identify the propagation trend of structural response in the spatial network. At the response level, a response scoring mechanism is constructed by combining propagation path strength, local response anomalies and structural critical location levels, and linkage between BIM model and edge devices is used to achieve linkage control operation.

[0047] The system exhibits higher interpretability and response robustness in situations where sensor density is limited, disturbance paths are complex, or responses are minor, making it suitable for long-term intelligent settlement monitoring during the renovation of old buildings, construction in complex geological conditions, and the operation of high-rise buildings in cities. Attached Figure Description

[0048] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0049] Figure 1 This is a flowchart of a building settlement detection method based on intelligent sensing disclosed in an embodiment of the present invention. Detailed Implementation

[0050] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0051] Example 1

[0052] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for detecting building settlement based on intelligent sensing, the method comprising:

[0053] S1. Acquire and preprocess structural response data and geological disturbance data from intelligent sensors to construct a structural response data set and a geological disturbance data set; wherein the intelligent sensors include tilt sensors, linear displacement sensors, resistance strain gauges, vibrating wire pore water pressure sensors, and three-component microseismic detectors.

[0054] Specifically, this step involves collecting and constructing the raw data inputs required for monitoring building structural settlement, including response-based sensor data from key structural components and disturbance-based sensor data from the geological environment. The most significant characteristics of data in building settlement scenarios are: heterogeneity of multiple physical quantities, inconsistent sampling frequencies, and discrete spatial distribution. Therefore, this step not only completes basic data collection but also specifically introduces a time synchronization mechanism and response change enhancement strategy to generate two structurally unified and time-aligned core datasets, S and G, providing complete input support for subsequent disturbance-structure modeling.

[0055] This step directly acquires the raw signal input from the sensor acquisition system. The structural response data comes from various types of sensors deployed at key structural locations (such as column bases, load-bearing wall bases, and foundation corners), specifically including:

[0056] Inclination sensors output triaxial inclination values ​​and are deployed on load-bearing component nodes;

[0057] Linear displacement sensors are installed at locations sensitive to foundation settlement and output absolute or relative displacement.

[0058] Resistance strain gauges are attached to the surface of structural components and read minute deformations through a bridge circuit.

[0059] Geological disturbance data are derived from data collected within the soil surrounding the building or at the boundary of the foundation pit.

[0060] Vibrating wire pore water pressure sensor is used to detect changes in groundwater pressure;

[0061] A three-component microseismic detector is used to capture microseismic disturbances and their propagation signals.

[0062] All sensor signals are uploaded via a field edge acquisition gateway. The system's default main sampling frequency is 1Hz, and the raw data needs to be time-aligned and structurally standardized.

[0063] Furthermore, the collected data is first structured into two sets: a structural response data set S and a geological disturbance data set G, constructed as follows:

[0064]

[0065] in, The tilt angle value of the i-th structural measuring point at time t is acquired by a triaxial inclinometer; The vertical displacement of the i-th structural measuring point comes from a linear displacement sensor; The strain value at the i-th structural measuring point is read by the strain gauge through a bridge circuit. The pore pressure value at the j-th geological disturbance measuring point; The main amplitude value of the microseismic wave at the j-th geological disturbance measuring point.

[0066] Because of the different sensor types, the original sampling frequencies also differ (e.g., 100Hz for micro-vibrations, 5Hz for strain, and 1Hz for tilt angle). The system performs time synchronization at the edge end using a unified time synchronization protocol (e.g., GPS or PTP) and constructs the main time axis {t}. k A unified sampling point is constructed using 1Hz as the frequency.

[0067] For microseismic data, the maximum amplitude is extracted within each 1-second window as the principal amplitude value at that time point:

[0068]

[0069] in: The high-frequency sampled value of the j-th measurement point in the original microseismic waveform; δ: time window, default is 1 second. For strain or other mid-frequency data (e.g., 5Hz), a weighted average is used to obtain the standard value:

[0070]

[0071] in, The raw subsampled values ​​of the strain gauge within 1 second before t; t k : Equal time intervals within the range [t-0.8, t]. If a sensor has no data at the main time point t, linear interpolation or nearest neighbor approximation is used to ensure that all... and Corresponding to the same moment, a unified synchronous snapshot is formed.

[0072] In addition, to enhance the system's ability to identify minute settlements, a response differential mechanism is introduced:

[0073]

[0074] in, The change in response of the i-th structural node within a time window τ (e.g., 10 seconds); The original three-dimensional response of structural node i at time t; The node's response status τ seconds ago.

[0075] This differential processing significantly enhances the system's sensitivity to micro-disturbances, enabling it to identify early settlement trends even with low deployment density. Ultimately, structural response and geological disturbance data form high-quality input pairs (S,G) on a unified master time axis, and combined with the on-site BIM model and coordinate calibration, generate a node location data table with geographic attributes.

[0076] Final output: S: Structural response data set, with dimensions N×3, and may include... G represents the dynamic response enhancement of the structural nodes; G: geological disturbance data set, with a dimension of M×2, including pore pressure and microseismic principal features; the two sets of data are fully aligned in time, have a unified format, and clear physical semantics, serving as direct input for the next step "disturbance-structure coupling modeling".

[0077] This step achieves the standardized construction of structural response and geological disturbance data in the building settlement monitoring system. To address issues such as time asynchrony, sensor heterogeneity, and difficulty in identifying micro-settlement in actual sampling, a comprehensive processing strategy including time-aligned interpolation and sliding differential enhancement mechanisms is proposed. This ensures that the generated S and G sets of data not only have engineering significance and structural consistency, but can also be directly input into subsequent coupled models without additional conversion processing.

[0078] S2. Collect the structural node coordinates and geological node coordinates of the actual measured building, and combine them with the structural response data set and geological disturbance data set to generate disturbance perception vectors of the structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response status of several structural nodes.

[0079] Specifically, the goal of this step is to construct a coupled model capable of accurately modeling the interaction between "disturbance and response," directly serving the key physical coupling reasoning stage in the "intelligent sensing-based building settlement detection system" described in the patent. In the previous step, we obtained a spatiotemporally aligned structural response data set S and a geological disturbance data set G. These two sets of data originate from the tilt angle, displacement, and strain measurements of key nodes in the building structure, and the pore water pressure and microseismic amplitude signals of the surrounding soil, respectively. There is no direct one-to-one correspondence between these two types of data in spatial structure, and the disturbance's influence on the structural response exhibits nonlinear, multi-scale, and delayed effects. Therefore, traditional direct fitting methods cannot be used for modeling.

[0080] To address this problem, a patentable and innovative modeling method is proposed in this step. This model integrates a spatially aware graph attention mechanism, a perturbation attenuation regularization term, and a structural node perturbation fusion strategy. It can adapt to the characteristics of sparse deployment, uneven perturbation, and structural heterogeneity under actual deployment conditions, and realize the functions of modeling perturbation propagation mechanism and response prediction.

[0081] This step uses the two main output variables from step one: Structural response data set, time-synchronized, three-dimensional structural state; Geological disturbance data set, time-synchronized, two-dimensional disturbance status;

[0082] The auxiliary input is the coordinates of the structural nodes. and geological node coordinates Provided by the actual layout and BIM model.

[0083] First, construct the initial topology of the perturbation-structure adjacency graph. For any perturbation source point g... j With structural response point s i With its three-dimensional Euclidean distance r j,i Calculate the intensity of the impact based on the following:

[0084]

[0085] Where: x j With x i These are the spatial coordinates of disturbance point j and structural point i, respectively; σ is the influence range control parameter, which is usually set according to the layout density. In this step, a physical attenuation term is introduced to weight the initial influence of disturbance point j on structural point i. Based on Euclidean distance, it reflects the real law that disturbance propagation attenuates with distance and is an important modeling strategy for the difference in response to disturbance near and far in house settlement.

[0086] Next, a trainable spatial attention mechanism is introduced to calculate the weighted action coefficients by combining perturbation features and structural location:

[0087]

[0088] Where: ψ(·) is a multilayer perceptron (MLP), and the input is the perturbation feature (obtained from geological perturbation data) and the relative spatial position x. j -x i splicing; The normalized propagation attention coefficient of perturbation point j to structure point i at time t; externally multiplied by It is an innovative enhancement mechanism that integrates physical laws and learning capabilities, strengthens spatial constraints, and improves model stability. and This is a disturbance characteristic.

[0089] This attention mechanism not only learns the strength of the impact of disturbances on the structure, but is also constrained by physical spatial relationships, thus better reflecting the transmission law of disturbances in real-world environments.

[0090] Finally, the disturbance sensing features received at each structural point are calculated.

[0091]

[0092] Wherein: the first term is the disturbance perception term, representing the direct impact of disturbances on structural nodes; the second term is the innovatively introduced structural local response difference regularization term. λ represents the spatial neighbors of structural point i; λ is the regularization weight used to control the simulation effect of the structural self-balancing response on disturbance absorption.

[0093] The design of this regularization term is based on engineering experience: structural settlement not only comes from external disturbances, but is also affected by the transmission and absorption of response differences between adjacent structural components. This invention captures the structural self-coordination mechanism at the data level, which has a strong realistic background in the patent scenario and can effectively simulate the propagation process of "local disturbance - structural absorption - global response".

[0094] Final output Response of the original structure Together, they serve as input features for downstream detection or recognition models. Essentially, this means that we not only focus on the "current state" of the structure, but also characterize "why the structure is in this state"—that is, the influence of external disturbances it has experienced. This is a causal reinforcement modeling approach.

[0095] Output: Each structural node i incorporates a disturbance-aware vector that integrates the difference between the disturbance effect and the structural response; The current response status of the structural node (from step one) will be compared with... Together they are used for subsequent identification and early warning modeling.

[0096] This step takes "perturbation-response" graph coupling modeling as its core, integrates the attenuation term of spatial physical distance, the learning attention mechanism, and the regularization term of the balance response between structures, and innovatively constructs an interpretable modeling framework for building settlement scenarios.

[0097] S3. Determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram. Based on the propagation probability matrix, infer the propagation path and intensity of settlement between structural nodes, and generate a structural settlement propagation map with directional edges and weights, as well as a propagation determination matrix.

[0098] Specifically, this step aims to utilize the perturbation sensing features obtained in step two. With structural response state Under the constraints of the building structure's connection topology, the potential propagation path of structural settlement is inferred, identifying "who caused it, where it propagates, and the intensity of propagation." Unlike traditional anomaly detection, settlement propagation exhibits structural topology, disturbance-driven characteristics, and temporal causality; therefore, it requires the integration of spatial structural diagrams. By combining on-site data features with a graph propagation reasoning mechanism for housing scenarios, a physically interpretable structural response evolution path model is constructed, providing a causal basis for the next step of risk warning strategy.

[0099] enter: The three-dimensional response state of structural node i is derived from step one; The disturbance perceived by structural node i at time t comes from step two; Structural connection diagram, where the nodes are structural measurement points and the edges represent the physical connection relationships between building components, which are exported from the BIM model; x i : Spatial coordinates of structural nodes, from layout calibration, which have been used in Step 2.

[0100] Among them, Structural connection diagram, where the node data corresponds to key measurement points in the building structure (such as column bases, bottom of load-bearing walls, foundation corners, etc.). Each node contains three-dimensional spatial coordinates (X, Y, Z) and component types (such as columns, beams, walls, etc.); Edge data: represents the physical connection relationships between components (such as the connection between columns and beams, the connection between walls and foundations). The attributes of the edges include connection types (rigid connection, hinge connection, etc.), force transfer characteristics, etc.

[0101] Furthermore, in this step, based on the structural connection diagram each node is appended with the current structural response state and its perceived disturbance characteristics to form the node state The goal is to infer the settlement propagation path between nodes based on the graph structure that is, whether there is a propagation trend from a certain node i to its neighbor j.

[0102] First, define the propagation probability matrix indicating the intensity of settlement influence transfer from node i to node j at time t:

[0103]

[0104] Among them: Similarity of structural node states, used to measure the coupling of adjacent node states; Indicator function, ensuring that propagation only occurs between node pairs with physical connections in the structure; The inclination value of node i (from ); γ, κ, λ: weight coefficients of the state similarity term, connection term, and structural potential energy term, respectively.

[0105] Among them, the third term is a newly designed settlement direction consistency regularization term, whose physical meaning is: if the inclination of the target node is larger than that of the source node, the propagation is unreasonable, so a penalty term is added. This reflects the basic fact that in actual engineering structures, settlement spreads gradually from weak points rather than in the reverse direction.

[0106] Then, define the propagation path judgment matrix

[0107]

[0108] Among them: τ: propagation intensity threshold, used to screen reliable propagation paths; This indicates whether a valid settlement propagation path exists from i to j. Finally, using the aforementioned propagation matrix, a settlement propagation diagram is constructed. Add a directed graph with directionality and propagation intensity to the structural connection graph. Its edges are... Border weight is Node status is

[0109] Output Structural settlement propagation pattern, including propagation direction and intensity; The propagation determination matrix is ​​used to generate propagation paths and risk path tracking.

[0110] S4. Based on the structural settlement propagation map, the current response status of the structural nodes, and the disturbance perception vector of the structural nodes, determine the risk score and classify it, and trigger the corresponding alarm and control actions.

[0111] This step aims to build upon the subsidence propagation map generated in the previous stage. With structural node state characteristics and characteristics of disturbance effects An event-driven settlement response decision-making mechanism is constructed to output the risk level of structural nodes and trigger corresponding control actions, achieving "closed-loop triggering" of settlement risk early warning. Unlike the traditional method based on single-node response numerical judgment, this step designs a response scoring mechanism based on propagation path accumulation + location classification + physical characteristic perception, and maps its output to specific response linkage commands, which has significant engineering adaptability and decision rationality.

[0112] This step starts from Extract all propagation paths Each path consists of several structural nodes. For each node i in the path, its response level depends on a comprehensive assessment of three dimensions: the node's local anomaly, the cumulative amount of path risk from propagation, and the node's physical criticality in the structural topology (e.g., its location at a foundation corner or main beam). We define a response risk score for structural nodes.

[0113]

[0114] in: A function that measures the difference between local response state and perturbation characteristics using weighted distance is used to capture potential anomalies in the node itself; Accumulated risk intensity of incoming paths obtained from the propagation graph structure; δ i : Physical criticality weight of node i, which can be marked by BIM (e.g., 1.0 for main load-bearing components and 0.5 for secondary nodes); α, β, γ: Control weights of three risk sources.

[0115] For example: a structural measurement point located at a fundamental corner, with a significant change in current tilt angle, and receiving information from multiple high-risk nodes at the end of the propagation path, its... If the value is significantly higher than other nodes, it will be identified as a high-risk node.

[0116] Will Substituting into the following hierarchical logic, we can map it to a specific response level:

[0117]

[0118] in: The risk level label for each node indicates a more severe response; τ1, τ2, τ3: These are grading thresholds set according to building type and regulations, for example, using an empirical formula τ. k =μ k +λ k σ (mean + standard deviation modulation).

[0119] According to level The system maps structure nodes to response linkage tables, as shown below (partial examples):

[0120] Risk level Corresponding linkage response 3 Send alarm + start basic grouting module + block passage structure 2 Push engineering team to the scene notification + enable monitoring enhancement 1 The system records and marks observation points, and prompts the duty personnel to pay attention 0 Only save the state, do not trigger response

[0121] Linkage commands are executed through edge devices (such as PLC controllers and grouting pump control systems), and their mapping tables are logically bound to the equipment numbers in the BIM model, ensuring high feasibility.

[0122] Example 2

[0123] This invention also provides a building settlement detection system based on intelligent sensing, the system comprising:

[0124] Data acquisition subsystem: used to acquire and preprocess structural response data and geological disturbance data from intelligent sensors to construct structural response datasets and geological disturbance datasets; wherein the intelligent sensors include tilt sensors, linear displacement sensors, resistance strain gauges, vibrating wire pore water pressure sensors, and three-component microseismic detectors;

[0125] Coupled modeling subsystem: used to collect the coordinates of structural nodes and geological nodes of the actual measured building, and combine the structural response data set and the geological disturbance data set to generate disturbance perception vectors of structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response state of several structural nodes;

[0126] Path reasoning subsystem: used to determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram, reason the propagation path and intensity of settlement between structural nodes based on the propagation probability matrix, generate a structural settlement propagation map with directional edges and weights, and a propagation determination matrix;

[0127] Risk Response Subsystem: This system combines the structural settlement propagation map, the current response status of structural nodes, and the disturbance perception vector of structural nodes to determine and classify risk scores, and trigger corresponding alarms and control actions.

[0128] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0130] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0131] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0137] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0139] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0140] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0141] Finally, it should be noted that the lithium battery pack chip equalization control platform disclosed in the embodiments of the present invention is only a preferred embodiment of the present invention and is only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting building settlement based on intelligent sensing, characterized in that, The method includes the following steps: S1. Acquire and preprocess structural response data and geological disturbance data from intelligent sensors to construct structural response data sets and geological disturbance data sets; wherein the intelligent sensors include tilt sensors, linear displacement sensors, resistance strain gauges, vibrating wire pore water pressure sensors, and three-component microseismic detectors; the geological disturbance data includes pore pressure values ​​and microseismic wave amplitude values ​​at geological disturbance measuring points; a response difference mechanism is introduced into the structural response data and geological disturbance data, by combining the current intelligent sensors within a time window. The internal response changes enhance the system's ability to identify minute settlements; S2. Collect the structural node coordinates and geological node coordinates of the actual measured building, and combine them with the structural response data set and geological disturbance data set to generate disturbance perception vectors of the structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response status of several structural nodes; S3. Determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram. Based on the propagation probability matrix, infer the propagation path and intensity of settlement between structural nodes, and generate a structural settlement propagation map with directional edges and weights, as well as a propagation determination matrix. S4. Based on the structural settlement propagation map, the current response status of the structural nodes, and the disturbance perception vector of the structural nodes, determine the risk score and classify it, and trigger the corresponding alarm and control actions.

2. The method for detecting building settlement based on intelligent sensing according to claim 1, characterized in that, The structural response data includes the time of structural measurement points. The tilt angle value, the vertical displacement of the structural measuring point, and the strain value of the structural measuring point; The preprocessing includes: For the main amplitude of the micro-seismic wave, the maximum amplitude is extracted within each 1-second window as the main amplitude value at the current time point; For the strain values ​​at the measuring points of the structure, a weighted average is used to obtain the standard value; If a sensor is at the main time point If no data is available, linear interpolation or nearest neighbor approximation is used to ensure that the structural response data set and the geological disturbance data set correspond to the same moment to form a unified synchronous snapshot.

3. The method for detecting building settlement based on intelligent sensing according to claim 1, characterized in that, S2 specifically includes: Calculate the three-dimensional Euclidean distance of any disturbance source point, and combine it with the current response state of the structural nodes to calculate the initial influence weight of the current disturbance point on the structural nodes; A trainable spatial attention mechanism is introduced to calculate weighted coefficients by combining perturbation features and structural location; the perturbation features are obtained by standardizing the geological perturbation data. By combining the initial influence weight, weighted action coefficient, and structural local response difference regularization term, the disturbance perception vector received by each structural node is calculated; wherein, the structural local response difference regularization term is calculated based on the current response state of the structural node and its adjacent structural nodes.

4. The method for detecting building settlement based on intelligent sensing according to claim 3, characterized in that, The trainable spatial attention mechanism is a multilayer perceptron, and the input is a concatenation of perturbation features and the relative spatial positions of perturbation points and structure points.

5. The method for detecting building settlement based on intelligent sensing according to claim 1, characterized in that, S3 specifically includes: Calculate the similarity of the states of structural nodes; It is determined that the current propagation only occurs between node pairs that are structurally connected. Calculate the tilt angle value based on the current response state of the structural node; The propagation probability matrix is ​​calculated by combining the structural node state similarity, judgment results, and tilt angle values, representing the time... The intensity of the settlement effect transmitted from the current node to adjacent nodes; If the propagation probability matrix is ​​determined to be greater than a preset threshold, then it is considered that there is an effective subsidence propagation path from the current node to the adjacent node. The resulting effective settlement propagation paths and propagation probability matrices construct a structural settlement propagation map; wherein, the node states of the structural settlement propagation map represent the current response states of the structural nodes.

6. The method for detecting building settlement based on intelligent sensing according to claim 1, characterized in that, The S4 specifically includes: Extract all propagation paths from the aforementioned structural settlement propagation map, wherein each path consists of several structural nodes; A weighted distance metric function that measures the difference between the current response state of the structural node and the perturbation sensing vector of the structural node; Calculate the cumulative intensity of incoming path risk obtained from the propagation graph; For each node in the path, the response risk score of the structural node is calculated by combining the weighted distance metric function, the cumulative strength of the input path risk, and the physical criticality weight. The response risk score is mapped to the corresponding response level. The structural nodes are mapped to the response linkage table according to the response level in order to execute the corresponding linkage response.

7. The method for detecting building settlement based on intelligent sensing according to claim 6, characterized in that, The corresponding response levels range from 0 to 3, with higher levels indicating more severe responses.

8. A method for detecting building settlement based on intelligent sensing according to claim 6, characterized in that, The corresponding linkage response includes issuing an alarm, starting the foundation grouting module, blocking the passage structure, notifying the engineering team to arrive on site, enabling enhanced monitoring, recording and marking key observation points in the system, prompting on-duty personnel to pay attention, and only saving the status without triggering a response.

9. A building settlement detection system based on intelligent sensing, characterized in that, The system includes: The data acquisition subsystem is used to acquire and preprocess structural response data and geological disturbance data from intelligent sensors to construct structural response datasets and geological disturbance datasets. The intelligent sensors include tilt sensors, linear displacement sensors, resistance strain gauges, vibrating wire pore water pressure sensors, and three-component microseismic detectors. The geological disturbance data includes pore pressure values ​​and microseismic wave amplitudes at geological disturbance measurement points. A response difference mechanism is introduced into the structural response data and geological disturbance data, combining the current intelligent sensor data within a time window. The internal response changes enhance the system's ability to identify minute settlements; Coupled modeling subsystem: used to collect the coordinates of structural nodes and geological nodes of the actual measured building, and combine the structural response data set and the geological disturbance data set to generate disturbance perception vectors of structural nodes by constructing a graph coupling model; wherein, the structural response data set includes the current response state of several structural nodes; Path reasoning subsystem: used to determine the propagation probability matrix based on the disturbance perception vector and the structural connection diagram, reason the propagation path and intensity of settlement between structural nodes based on the propagation probability matrix, generate a structural settlement propagation map with directional edges and weights, and a propagation determination matrix; Risk Response Subsystem: This system combines the structural settlement propagation map, the current response status of structural nodes, and the disturbance perception vector of structural nodes to determine and classify risk scores, and trigger corresponding alarms and control actions.

Images