A construction safety monitoring method, device and medium based on the Internet of Things

Abstract

The embodiment of the specification discloses a construction safety monitoring method and device based on Internet of Things, medium, relates to the technical field of Internet of Things, and is used for solving the problem that the existing monitoring method is not comprehensive and reliable. The method comprises the following steps: according to the static sensing nodes deployed in the current pipeline construction area and the dynamic sensing nodes deployed in each mobile machine, the current pipeline construction area is spatially divided to obtain a monitoring grid; based on the monitoring data collected by each sensor and the space-time correspondence relationship between the monitoring data and the monitoring grid, a safety risk source grid unit of the current pipeline construction area is identified; the mechanical conduction characteristics in the monitoring data are extracted to simulate a safety risk spread path corresponding to each safety risk source grid unit; according to the current pipeline construction scheme information and the safety risk spread path, a key risk grid unit is identified, and a warning dispatch is performed on the construction management terminal of the key risk grid unit.

Description

Technical Field

[0001] This specification relates to the field of Internet of Things (IoT) technology, and in particular to a construction safety monitoring method, equipment, and medium based on IoT. Background Technology

[0002] With the rapid development of social infrastructure construction, pipeline projects, especially long-distance, large-diameter oil and gas and water pipeline projects, are increasing. These projects involve complex geological conditions and spatial formations along their routes, alternating between underground and overhead laying. Underground operations face risks such as slope instability, uneven soil stress leading to localized settlement or even collapse. Overhead operations face risks such as deformation and instability of temporary support structures and the risk of heavy objects falling from heights. Due to the complex construction environment, diverse types of machinery involved, and frequent movement of equipment in both underground and overhead laying, numerous and dynamic factors related to safety risks arise during construction. Traditional manual inspection and static monitoring methods are no longer sufficient to meet the high demands of modern engineering for real-time, accurate, and predictable safety management.

[0003] Currently, common IoT monitoring solutions mainly rely on the fixed deployment of various sensors or cameras in construction areas to form a static monitoring network. These systems can continuously collect environmental and structural data of the construction area and transmit it to the monitoring center via the network to achieve preliminary risk identification and alarm. However, mobile machinery such as excavators, cranes, and transport vehicles in the construction area are themselves significant sources and carriers of risk, and their movement trajectories and operating states are dynamically changing. The lack of effective spatiotemporal correlation between the static sensor network and dynamic objects makes it impossible to effectively and continuously track the state changes of these mobile objects and their surrounding environment, creating blind spots in dynamic monitoring. At the same time, current monitoring methods mostly stop at simple alarms for single sensor data exceeding thresholds, or simply listing multiple independent alarm points. This method cannot correlate multiple risk events in a spatiotemporal dimension, making it difficult to accurately determine the true origin of the risk, resulting in delayed early warnings and preventing managers from taking precise intervention measures before the risk escalates. Summary of the Invention

[0004] To address the aforementioned technical problems, this specification provides one or more embodiments of a construction safety monitoring method, device, and medium based on the Internet of Things.

[0005] One or more embodiments of this specification employ the following technical solutions: This specification provides one or more embodiments of a construction safety monitoring method based on the Internet of Things, the method including: Based on the static sensing nodes deployed in the current pipeline construction area and the dynamic sensing nodes deployed in various mobile machines, the current pipeline construction area is spatially divided to obtain a monitoring grid. Based on the monitoring data of the current pipeline construction area collected by each sensor, and the spatiotemporal correspondence between the monitoring data and the monitoring grid, the safety risk origin grid unit of the current pipeline construction area is identified; Mechanical transmission characteristics are extracted from the monitoring data to simulate the safety risk propagation path corresponding to each safety risk origin grid cell; wherein, the mechanical transmission characteristics are matched with the risk type of the safety risk origin grid cell; Based on the pipeline construction plan information of the current pipeline construction area and the safety risk propagation path, key risk grid units are identified, and early warning scheduling is performed on the construction management terminals of the key risk grid units.

[0006] Optionally, in one or more embodiments of this specification, based on the monitoring data of the current pipeline construction area collected by each sensor, and the spatiotemporal correspondence between the monitoring data and the monitoring grid, the safety risk origin grid unit of the current pipeline construction area is identified, specifically including: Based on the timestamps corresponding to the monitoring data collected by each static sensing node and each dynamic sensing node, the monitoring data is time-aligned, and based on the spatial location of the monitoring data in the monitoring grid, the monitoring data is spatially registered to obtain a unified spatiotemporal monitoring data sequence. Based on a preset sliding time window, feature extraction is performed on the spatiotemporal monitoring data sequence corresponding to each grid unit to obtain the monitoring feature vector of each spatiotemporal monitoring data sequence. Based on the distance between the monitoring feature vector and the preset risk feature vector, candidate risk monitoring grid units with security risks are determined. Spatiotemporal clustering is performed on the candidate risk monitoring grid units to merge candidate risk monitoring grid units that are spatiotemporally adjacent and have similar monitoring feature vectors, thereby obtaining the risk cluster of the current pipeline construction area; Obtain the monitoring feature vectors of each candidate risk monitoring grid unit within the risk cluster in multiple consecutive preset sliding time windows; The risk probabilities of each monitoring feature vector are arranged according to the sequence of consecutive preset sliding time windows to obtain the risk probability time series of each candidate risk monitoring grid unit. The grid unit corresponding to the mutation point of the risk probability time series is used to determine the grid unit of the origin of the safety risk.

[0007] Optionally, in one or more embodiments of this specification, extracting the mechanical transmission characteristics from the monitoring data specifically includes: The risk type of the safety risk originating grid cell is determined, and a corresponding mechanical transmission index is matched according to the risk type; wherein, the mechanical transmission index includes: stress transmission coefficient, strain diffusion rate, displacement transmission attenuation rate, and load transmission path curvature; The spatiotemporal monitoring data sequence is filtered to obtain the specified monitoring data corresponding to the mechanical transmission index; Based on the specified monitoring data corresponding to the safety risk origin grid cell and the adjacent monitoring grid, the values ​​of each mechanical transmission index are determined; The values ​​of each of the aforementioned mechanical transmission indices are normalized to obtain the mechanical transmission characteristics corresponding to the grid cells from which the safety risks originate.

[0008] Optionally, in one or more embodiments of this specification, the current pipeline construction area is spatially divided into a monitoring grid based on static sensing nodes deployed in the current pipeline construction area and dynamic sensing nodes deployed on various mobile machines, specifically including: Acquire the fixed monitoring performance information of static sensing nodes deployed in the current pipeline construction area, and the real-time monitoring performance information of dynamic sensing nodes deployed in various mobile machinery. Based on the fixed monitoring performance information of static sensor nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensor nodes deployed in various mobile machinery, spatial clustering is performed to divide the current pipeline construction area into a monitoring grid; wherein, the monitoring network includes two layers: a static grid and a dynamic grid.

[0009] Optionally, in one or more embodiments of this specification, spatial clustering is performed based on the fixed monitoring performance information of static sensing nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensing nodes deployed on various mobile machines to divide the current pipeline construction area into a monitoring grid, specifically including: Based on the fixed monitoring performance information of the static sensor nodes, determine the fixed monitoring position and monitoring range of each static sensor node; Based on the monitoring location and the monitoring range, the static sensing nodes are clustered to obtain the static grid cells of the current pipeline construction area; Based on the monitoring information of the dynamic sensing nodes, determine the position coordinates and mechanical operation limit range of each dynamic sensing node, and determine the dynamic monitoring coverage area corresponding to each dynamic sensing node based on the position coordinates and the mechanical operation limit range. The dynamic monitoring coverage area of ​​the same mobile machinery's dynamic sensing nodes within a preset time window is divided into dynamic grid units; wherein, the boundary of the dynamic grid unit is generated by fitting the movement trajectory of the mobile machinery. The static and dynamic grid units are mapped to a preset spatial coordinate system, a grid unit association table is established, the spatial overlap relationship between the dynamic and static grid units is obtained, and a monitoring network corresponding to the current pipeline construction area is generated.

[0010] Optionally, in one or more embodiments of this specification, simulating the security risk propagation path corresponding to each security risk originating grid cell specifically includes: Based on the spatial overlap relationship between static and dynamic grid units in the grid unit association table, each monitoring grid unit is taken as a node, the connection relationship between adjacent grid units is taken as an edge, and the weight of the edge is obtained based on the mechanical transmission characteristics between the grid unit where the safety risk originates and the adjacent grid units, so as to generate the risk spread topology network of the current pipeline construction area. Based on the characteristics of mechanical transmission, an initial risk transmission function is established, and the initial risk transmission function is modified according to the pipeline construction plan information of the current pipeline construction area to obtain the risk transmission function. Substitute the grid cells representing the origin of security risks into the risk transmission function to obtain the cumulative risk intensity of adjacent grid cells according to a preset period; If the risk accumulation intensity of the adjacent grid cell is determined to be greater than a preset risk threshold, then the adjacent grid cell is determined to be a risk propagation node. Based on the real-time monitoring performance information of the flowing machinery fed back by each dynamic grid cell, the node position and edge weight of the dynamic grid cell are updated. The risk accumulation intensity of adjacent grid cells is obtained iteratively based on the updated node position and edge weight to supplement and update the risk spread nodes. Based on the determined time corresponding to each security risk origin grid cell and each risk spread node, the security risk origin grid cells and each risk spread node are connected to obtain the security risk spread path corresponding to each security risk origin grid cell.

[0011] Optionally, in one or more embodiments of this specification, based on the pipeline construction plan information of the current pipeline construction area and the safety risk propagation path, key risk grid cells are identified, specifically including: Key construction elements are extracted from the pipeline construction plan information. Based on the location information corresponding to the key construction elements and the monitoring grid units covered by each safety risk propagation path, risk propagation grid units that spatially overlap with the key construction elements are identified as candidate key risk grid units. Based on the construction schedule within the pipeline construction scheme information, determine the time sensitivity value of the construction activities corresponding to each candidate key risk grid unit; By combining the risk accumulation intensity of each risk propagation node in the security risk propagation path with the time sensitivity value of the corresponding candidate key risk grid unit, the comprehensive risk assessment value of each candidate key risk grid unit is determined. The comprehensive risk assessment value is compared with the preset key risk threshold. If the comprehensive risk assessment value is greater than the preset key risk threshold, the corresponding candidate key risk grid cell is determined as a key risk grid cell.

[0012] Optionally, in one or more embodiments of this specification, early warning scheduling is performed on the construction management terminal of the key risk grid unit, specifically including: Based on the pre-set hierarchical response mechanism, the early warning instructions corresponding to the key risk grid units are determined, and the handling map of the key risk grid units is determined based on the spatial distribution characteristics of the key risk grid units. The warning instruction and the handling map are sent to the construction management terminal of the key risk grid unit to obtain feedback data from the construction management terminal; The response map is updated based on the feedback data to enable early warning and scheduling of the current pipeline construction area.

[0013] This specification provides one or more embodiments of an Internet of Things (IoT)-based construction safety monitoring device, the device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described above.

[0014] This specification provides one or more embodiments of a non-volatile computer storage medium storing computer-executable instructions, the computer-executable instructions being configured to execute any of the methods described above.

[0015] The above-described at least one technical solution used in the embodiments of this specification can achieve the following beneficial effects: Spatial clustering is performed using the fixed monitoring performance information of static sensor nodes and the real-time monitoring performance information of dynamic sensor nodes to achieve the division of the monitoring grid in the current pipeline construction area. This enables refined coverage of the monitoring area. The static grid ensures stable monitoring of fixed construction areas, while the dynamic grid adjusts in real time to follow the mobile machinery, avoiding monitoring blind spots and adapting to both fixed areas and mobile operations in pipeline construction. Based on the spatiotemporal correspondence between sensor monitoring data and the monitoring grid, the grid units for the origin of safety risks are identified, solving the problems of ambiguous risk sources and difficulty in tracing the source in traditional monitoring. Mechanical transmission characteristics are extracted from the monitoring data. By simulating the risk propagation path of the grid units for the origin of safety risks, the evolution of risks can be predicted, helping construction parties to know the direction and scope of risk spread in advance and avoid further risk propagation. Combining pipeline construction plan information with the safety risk propagation path, key risk grid units are identified and early warning scheduling is implemented on the construction management terminal. This allows early warning scheduling to be deeply adapted to the construction process, ensuring that early warning measures do not interfere with normal construction and achieving a balance between safety and efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 A flowchart illustrating an IoT-based construction safety monitoring method provided in this specification's embodiments; Figure 2 A schematic diagram of the structure of an Internet of Things-based construction safety monitoring device provided as an embodiment of this specification; Figure 3 This is a schematic diagram of the structure of a non-volatile storage medium provided in the embodiments of this specification. Detailed Implementation

[0017] This specification provides an embodiment of a construction safety monitoring method, equipment, and medium based on the Internet of Things.

[0018] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0019] like Figure 1 As shown in the figure, this specification provides a schematic flowchart of a construction safety monitoring method based on the Internet of Things. Figure 1 As can be seen, in one or more embodiments of this specification, a construction safety monitoring method based on the Internet of Things specifically includes the following steps: S101: Based on the static sensing nodes deployed in the current pipeline construction area and the dynamic sensing nodes deployed in various mobile machines, the current pipeline construction area is spatially divided to obtain a monitoring grid.

[0020] In one embodiment, due to the vast area and complex terrain of pipeline construction zones, efficient and blind-spot-free monitoring requires scientific spatial planning of sensor node deployment. One approach involves engineers dividing the site into regular geometric grids as monitoring grids before construction, based on design drawings and their experience, according to the defined operational ranges of static sensors deployed in the current pipeline construction area and dynamic sensors deployed on various mobile machinery. However, because pipeline construction areas are vast and environmentally complex, a single fixed monitoring mode cannot effectively cover the entire area, especially for the operational areas of mobile machinery such as excavators and cranes, where risks are dynamically changing. Therefore, relying solely on traditional monitoring methods or static sensor monitoring may create monitoring blind spots. Furthermore, relying solely on the monitoring of the mobile machinery itself makes it difficult to correlate and analyze with the overall, fixed construction environment. Therefore, to construct a monitoring method that is both comprehensive and accurately captures dynamic risks, spatial clustering can be performed on the fixed monitoring performance information of static sensor nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensor nodes deployed in various mobile machinery. This allows for the division of the current pipeline construction area into a monitoring grid. It should be noted that the monitoring network comprises two layers: a static grid and a dynamic grid. That is, after obtaining static grid units based on the fixed monitoring performance information of the static sensor nodes in the current pipeline construction area and dynamic grid units based on the real-time monitoring performance information of the dynamic sensor nodes deployed in various mobile machinery, these units are mapped to the same pre-defined spatial coordinate system of the construction area. By calculating the spatial relationships between them, a grid unit association table is established, thus forming a dynamic and static combined monitoring network that includes both static and dynamic grids.

[0021] Specifically, due to the spatial and data heterogeneity between static and dynamic nodes, direct fusion analysis would lead to computational complexity and positioning ambiguity. Therefore, to address the needs of handling large-scale, combined static and dynamic construction monitoring, in one or more embodiments of this specification, the fixed monitoring performance information of static sensing nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensing nodes deployed on various mobile machinery are spatially clustered to divide the current pipeline construction area into a monitoring grid. This specifically includes the following steps: First, based on the fixed monitoring performance information of the static sensor nodes, the fixed monitoring positions and monitoring ranges of each static sensor node are determined. Then, based on the monitoring positions and ranges, the static sensor nodes are clustered to obtain static grid cells for the current pipeline construction area. In one embodiment, the fixed monitoring position of each node can be used as the cluster center, and an initial cluster radius can be determined based on its monitoring range. Nodes with overlapping monitoring ranges are then merged to form a static node cluster. Next, the convex hull formed by each static sensor node in this static node cluster is obtained. Based on the boundaries of each convex hull, the boundaries of the static grid are determined, and static grid cells based on these boundaries are obtained. The coverage areas of adjacent static grid cells thus divided have no overlap and no monitoring blind spots.

[0022] Simultaneously, based on the fixed monitoring performance information of the dynamic sensing nodes, the position coordinates of each dynamic sensing node and the mechanical operation limit range are determined. This allows for the determination of the dynamic monitoring coverage area corresponding to each dynamic sensing node based on the position coordinates and the mechanical operation limit range. The system will form a dynamic monitoring coverage area for the movement trajectory of each mobile machine within a preset time window. The boundary of this area is not a simple superposition of circles, but rather a polygonal envelope generated by fitting the movement trajectory of the dynamic monitoring coverage area of ​​the same mobile machine's dynamic sensing nodes within the preset time window. This divides the dynamic monitoring coverage area of ​​the same mobile machine's dynamic sensing nodes within the preset time window into dynamic grid cells. After generating static and dynamic grid cells respectively, it is necessary to map the static and dynamic grid cells to the same preset spatial coordinate system. By calculating their spatial positional relationship, a grid cell association table between static and dynamic grid cells is established. It is understandable that the grid cell association table records which dynamic grid cell is covering or close to which static grid cell, thereby obtaining the spatial overlap relationship between the dynamic and static grids. Based on this spatial overlap relationship, the static and dynamic grid cells and their spatial relationship can be used to generate the monitoring network corresponding to the current pipeline construction area.

[0023] This process integrates the monitoring capabilities of individual nodes into collaborative monitoring of grid cells through clustering and convex hull calculation based on the monitoring range. This ensures non-overlapping and blind-spot-free coverage within a fixed area, enabling the effective capture of any environmental anomalies within the static grid. Furthermore, by fitting the movement trajectory and the defined range of mechanical operations, such as the working radius of an excavator, into dynamic grid cells, the time-varying risk range brought by mobile devices like excavators and cranes is accurately characterized, achieving effective monitoring of dynamic risks. Moreover, mapping static and dynamic grid cells to the same preset spatial coordinate system transforms the spatial relationship between the static environment and dynamic activities into an explicit correlation. This clarifies the connection between the static environment and dynamic activities, avoiding the problems of complex subsequent calculations and unclear physical meaning caused by the heterogeneity of data sources, accuracy, and properties when directly correlating the latitude and longitude of static and dynamic sensors.

[0024] S102: Based on the monitoring data of the current pipeline construction area collected by each sensor, and the spatiotemporal correspondence between the monitoring data and the monitoring grid, identify the safety risk origin grid unit of the current pipeline construction area.

[0025] Due to the complex environment of pipeline construction areas, risks are characterized by their concealment and diffusion. Traditional monitoring can only acquire scattered data and cannot correlate data with the spatiotemporal relationship of the construction area. This makes it difficult to quickly locate the initial grid cell where safety risks such as pipeline leaks and structural deformations occur, delaying response and escalating losses. Therefore, the embodiments in this specification utilize multiple types of sensors at static sensor nodes (pressure, vibration, temperature, displacement, etc.) and dynamic sensor nodes to collect real-time, multi-dimensional monitoring data of the current pipeline construction area, ensuring data coverage of the entire construction scenario. Based on the acquired monitoring data and the spatiotemporal correspondence between the monitoring data and the monitoring grid, grid cells with abnormal data are filtered out, thereby identifying the grid cell from which the safety risks in the current pipeline construction area originate.

[0026] Specifically, in one or more embodiments of this specification, since the risk evolution in a pipeline construction area is a dynamic process, an abnormal reading from a single sensor at a single moment may only be a momentary disturbance, while the true origin of the risk often has continuity and diffusion in the spatiotemporal dimension. Responding only to isolated alarms may lead to frequent false alarms and an inability to pinpoint the root cause of the risk. However, when a risk first emerges, its signal characteristics are weak and easily masked by environmental noise. Therefore, in order to accurately capture the true initiation point of the risk from massive heterogeneous monitoring data, the process described above for identifying the safety risk origin grid unit based on the spatiotemporal correspondence between monitoring data and the monitoring grid, based on the monitoring data of the current pipeline construction area collected by each sensor and the spatiotemporal correspondence between the monitoring data and the monitoring grid, can be specifically performed in the following manner: The monitoring data for the construction area comes from static and dynamic sensor nodes. The acquisition time and spatial location of different nodes vary, and direct use of this data can lead to biased analysis results. Therefore, in this embodiment, the monitoring data is time-aligned based on the timestamps corresponding to the monitoring data collected by each static and dynamic sensor node, and spatially registered based on the spatial location of the monitoring data within the monitoring grid, resulting in a unified spatiotemporal monitoring data sequence. In other words, if a grid cell collects data from multiple sensors within a specific time window, this data is integrated into a spatiotemporal monitoring data sequence for that grid cell within that time period. Then, a preset sliding time window is used to sequentially extract the spatiotemporal monitoring data sequence corresponding to each grid cell. Feature extraction is performed on the data within each window to generate a monitoring feature vector that comprehensively characterizes the safety status of the grid cell within that time period. Then, the similarity between the current grid cell's state and known risks is determined based on the cosine or Euclidean distance between the monitoring feature vector and a preset risk feature vector. If this distance is less than a preset risk judgment threshold, then the grid cell is considered a candidate risk monitoring grid cell with safety risks within that time window. Since the identified candidate risk grid cells may be spatially and temporally dispersed, spatiotemporal clustering is required to merge spatiotemporally adjacent candidate risk monitoring grid cells with similar monitoring feature vectors, thus obtaining risk clusters in the current pipeline construction area. This helps avoid misclassifying the same continuously spreading risk as multiple isolated events. To accurately locate the origin point from the risk cluster, the system backtracks the monitoring feature vectors of each grid cell within that cluster across multiple consecutive sliding time windows. Based on the order of the consecutive preset sliding time windows, the risk probability calculated for each window (i.e., its similarity to the preset risk feature vector) is arranged, generating a risk probability time series for each candidate grid cell. It should be noted that the true risk origin point will exhibit the earliest abrupt change in its risk probability time series. Therefore, the safety risk origin grid cell needs to be determined based on the monitoring grid corresponding to the abrupt change in the risk probability time series. Furthermore, the abrupt change point can be identified using methods such as CUSUM and sliding window T-tests to pinpoint the time point when the probability first significantly increases in each sequence.

[0027] By constructing a unified spatiotemporal data sequence, multi-source heterogeneous monitoring data is integrated into a structured grid model, effectively eliminating information silos. Furthermore, through temporal feature extraction and pattern matching, true risk precursors can be accurately identified from complex and noisy environments, significantly reducing false alarms and missed alarms. Through spatiotemporal clustering and abrupt change point backtracking analysis, not only can the complete impact range of the risk be outlined, but the earliest origin point of the risk in the spatiotemporal dimension can also be precisely located. This transforms safety management from a passive response to scattered alarms into an early intervention from the source of risk spread, effectively curbing further risk escalation and enhancing the initiative and accuracy of overall construction safety management.

[0028] S103: Extract the mechanical transmission characteristics from the monitoring data to simulate the safety risk propagation path corresponding to each safety risk origin grid unit; wherein the mechanical transmission characteristics are matched with the risk type of the safety risk origin grid unit.

[0029] Because the risks in pipeline construction areas are not static and isolated, but rather continuously propagate and evolve within a spatial and temporal range according to physical laws. For example, excessive soil stress at one point can lead to a redistribution of stress to surrounding areas, potentially triggering a chain reaction of instability; the vibration energy of a heavy piece of equipment can propagate through the strata, affecting distant pipeline interfaces. If only the origin of a risk is identified without predicting its spread, early warning and response will always lag behind the risk's development. Therefore, in order to achieve proactive perception and precise intervention of risk dynamics in the embodiments of this specification, mechanical transmission characteristics are extracted from monitoring data to simulate the safety risk spread path corresponding to each safety risk origin grid unit. It should be noted that different risk types have different dominant transmission physical mechanisms, so the mechanical transmission characteristics are matched with the risk type of the safety risk origin grid unit.

[0030] Specifically, in one or more embodiments of this specification, extracting the mechanical transmission characteristics from the monitoring data includes: After identifying the grid cells from which safety risks originate and their risk types, corresponding mechanical transmission indicators are matched accordingly. These indicators include stress transmission coefficient, strain diffusion rate, displacement transmission attenuation rate, and load transmission path curvature. For example, for the risk of heavy machinery disturbance, the mechanical transmission indicators might include vibration energy attenuation rate and displacement transmission attenuation rate. For the risk of pipeline structure deformation, the mechanical transmission indicators might include load transmission path curvature. From a unified spatiotemporal monitoring data sequence, designated monitoring data related to these selected indicators are selected. Based on the designated monitoring data between the safety risk origin grid cells and their adjacent grid cells, the specific values ​​of each mechanical transmission indicator are calculated using physical models or empirical formulas, and finally normalized to form a set of quantitative mechanical transmission characteristics. This allows for a quantitative description of the ease and direction of risk diffusion from the origin point to the surrounding areas.

[0031] Specifically, in one or more embodiments of this specification, since the identified safety risk origin grid cell is only the starting point of the risk, and the risk will spread within the current pipeline construction area according to certain physical laws, without predicting its spread trend, all early warnings and responses will be delayed and reactive. Therefore, in order to achieve advanced perception and precise deployment of dynamic risk evolution, the process of simulating the safety risk spread path corresponding to each safety risk origin grid cell can be implemented based on the following process: Based on the spatial overlap between static and dynamic grid units in the grid unit association table, each monitoring grid unit is used as a node, and the connections between adjacent grid units are used as edges. Simultaneously, the weights of the edges are obtained based on the mechanical transmission characteristics between the grid unit where the safety risk originates and its adjacent grid units. These mechanical transmission characteristics need to be comprehensively calculated in conjunction with factors such as pipeline material, soil properties, and construction medium. It can be understood that the mechanical transmission characteristics directly reflect the efficiency and intensity of risk transmission between grid units. Therefore, the weight ratio of the corresponding mechanical transmission characteristics can be determined according to the risk type of the grid unit where the safety risk originates. Then, the weights of the edges are obtained by weighted summation based on the weight ratios of each mechanical transmission characteristic. Finally, based on the determined edge weights, a risk propagation topology network for the current pipeline construction area is generated that accurately reflects the spatial correlation and risk transmission resistance of the region, providing a spatial carrier for subsequent risk propagation simulations. Based on the characteristics of mechanical transmission, an initial risk transmission function is first established. This function uses risk origin intensity, mechanical transmission coefficient, and grid cell spacing as core parameters to describe the basic transmission law of risk between adjacent grid cells. The mechanical transmission coefficient needs to be calibrated through extensive pipeline construction risk simulation experiments and field measurement data to ensure that the function initially matches the physical characteristics of risk propagation. Subsequently, the initial risk transmission function is modified based on pipeline construction plan information for the current pipeline construction area. Construction plan information includes pipeline laying depth, welding process, support structure settings, and construction machinery operation routes, which directly affect the path and efficiency of risk transmission. A risk transmission function matching the current pipeline construction scenario is obtained through targeted modification. The identified safety risk origin grid cells are substituted into the modified risk transmission function, and the cumulative risk intensity of adjacent grid cells is continuously calculated and obtained according to a preset period. If the cumulative risk intensity of adjacent grid cells is determined to be greater than a preset risk threshold, the adjacent grid cells are identified as risk propagation nodes, indicating that the risk has spread from the origin unit to the area. Because the pipeline construction area contains mobile machinery such as excavators, cranes, and welding equipment, the movement of these devices changes the spatial position of dynamic grid cells and affects the mechanical transmission environment of the surrounding area. Therefore, it is necessary to dynamically update the node positions and corresponding edge weights of the dynamic grid cells based on the real-time monitoring performance information of the mobile machinery fed back by each dynamic grid cell, such as the machine position coordinates, work intensity, and equipment weight. Then, based on the updated node positions and edge weights, the risk transmission function is re-substituted to iteratively calculate the risk accumulation intensity of adjacent grid cells. Newly added grid cells that meet the risk threshold requirements are supplemented and marked to realize the dynamic updating of risk spread nodes and ensure that the risk spread simulation can adapt to the dynamic changes of the construction area in real time.It should be noted that when dynamically updating the node positions of dynamic grid cells and the weights of corresponding edges in the topology network, in certain scenarios, such as the area where mobile machinery stops, the edge weights need to be adjusted according to the mechanical transmission characteristics based on the weight of the machinery, and the node connection relationships in the area of ​​the machinery's movement trajectory need to be updated in real time. After realizing the dynamic updating of risk propagation nodes, based on the determination time of each safety risk origin grid cell (that is, the time when the risk origin is identified) and the determination time corresponding to each risk propagation node (that is, the time when the risk accumulation intensity of the node first exceeds the threshold), the safety risk origin grid cells and their corresponding risk propagation nodes are logically connected in chronological order to obtain the safety risk propagation path corresponding to each safety risk origin grid cell, providing a clear basis for subsequent early warning and precise deployment.

[0032] S104: Based on the pipeline construction plan information of the current pipeline construction area and the safety risk propagation path, identify key risk grid units and perform early warning scheduling for the construction management terminals of the key risk grid units.

[0033] Due to limited construction resources, responding equally to all grid cells along all risk spread paths is uneconomical and inefficient. Risk spread paths only reveal the trend of risk propagation but do not indicate which points will have the most severe consequences. If early warning information lacks prioritization, critical areas may not be addressed in a timely manner, leading to significant losses. Therefore, to achieve optimal allocation of early warning resources and precise and efficient emergency response, after obtaining the safety risk spread paths, key risk grid cells can be identified based on the pipeline construction plan information of the current pipeline construction area and the safety risk spread paths. Early warning scheduling can then be implemented for the construction management terminals of these key risk grid cells. Specifically: All grid cells covered by the safety risk contagion path are spatially overlaid with key construction elements extracted from pipeline construction plan information. These elements include, but are not limited to: pipeline welding work areas, pipeline pressure testing areas, deep foundation pit work areas, temporary support structure installation locations, areas with high concentrations of construction personnel, and important equipment storage areas. Any risk contagion grid cell that spatially overlaps with these key elements is initially screened as a candidate key risk grid cell. Then, based on the construction schedule in the construction plan, each candidate cell is assigned a time sensitivity score. For example, a work area where pipeline welding will be carried out within the next 2 hours has a much higher time sensitivity score than a work area where backfilling will not be carried out for 3 days; cells within the critical process window will receive the highest score. Combining the risk accumulation intensity of the candidate cell in the risk contagion path and the order in which it is marked, the urgency of the risk is determined. Thus, based on the time sensitivity score and the risk accumulation intensity and location reflecting the urgency of the risk, a comprehensive risk assessment value is calculated. This value is compared with a preset critical risk threshold. Candidate units that exceed the threshold are finally identified as critical risk grid units, and their risk levels are classified according to their comprehensive evaluation values.

[0034] Identifying key risk grid units is only the first step. If early warning instructions are simplistic and response plans are rigid, they will struggle to handle complex on-site situations, potentially leading to delayed responses or overreactions. Therefore, to achieve a seamless closed loop from risk early warning to coordinated response, the process of scheduling early warnings for construction management terminals of key risk grid units after identification can be implemented based on the following steps: Based on a pre-set tiered response mechanism, early warning instructions corresponding to key risk grid units are determined, and a response map for each key risk grid unit is established based on its spatial distribution characteristics. This map not only indicates the location and level of risk points but also intelligently recommends scheduling paths for response resources, personnel evacuation routes, and collaborative response plans based on construction plans and resource layout. Then, the early warning instructions and response map are sent to the construction management terminal of the key risk grid unit to obtain feedback data and dynamically update the initial response map. This updated map enables early warning scheduling for the current pipeline construction area.

[0035] like Figure 2 As shown in the diagram, this specification provides a structural schematic of an IoT-based construction safety monitoring device. Figure 2 As can be seen, in one or more embodiments of this specification, a construction safety monitoring device based on the Internet of Things includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described above.

[0036] like Figure 3 As shown, this specification provides a non-volatile storage medium storing computer-executable instructions 301, which are capable of executing any of the methods described above.

[0037] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, and therefore described more simply; relevant parts can be referred to the descriptions of the method embodiments.

[0038] 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 recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0039] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A construction safety monitoring method based on the Internet of Things, characterized in that, The method includes: Based on the static sensing nodes deployed in the current pipeline construction area and the dynamic sensing nodes deployed in various mobile machines, the current pipeline construction area is spatially divided to obtain a monitoring grid. Based on the monitoring data of the current pipeline construction area collected by each sensor, and the spatiotemporal correspondence between the monitoring data and the monitoring grid, the safety risk origin grid unit of the current pipeline construction area is identified; Mechanical transmission characteristics are extracted from the monitoring data to simulate the safety risk propagation path corresponding to each safety risk origin grid cell; wherein, the mechanical transmission characteristics are matched with the risk type of the safety risk origin grid cell; Based on the pipeline construction plan information of the current pipeline construction area and the safety risk propagation path, key risk grid units are identified, and early warning scheduling is performed on the construction management terminals of the key risk grid units. Based on the monitoring data of the current pipeline construction area collected by each sensor, and the spatiotemporal correspondence between the monitoring data and the monitoring grid, the safety risk origin grid cells of the current pipeline construction area are identified, specifically including: Based on the timestamps corresponding to the monitoring data collected by each static sensing node and each dynamic sensing node, the monitoring data is time-aligned, and based on the spatial location of the monitoring data in the monitoring grid, the monitoring data is spatially registered to obtain a unified spatiotemporal monitoring data sequence. Based on a preset sliding time window, feature extraction is performed on the spatiotemporal monitoring data sequence corresponding to each grid unit to obtain the monitoring feature vector of each spatiotemporal monitoring data sequence. Based on the distance between the monitoring feature vector and the preset risk feature vector, candidate risk monitoring grid units with security risks are determined. Spatiotemporal clustering is performed on the candidate risk monitoring grid units to merge candidate risk monitoring grid units that are spatiotemporally adjacent and have similar monitoring feature vectors, thereby obtaining the risk cluster of the current pipeline construction area; Obtain the monitoring feature vectors of each candidate risk monitoring grid unit within the risk cluster in multiple consecutive preset sliding time windows; According to the sequence of consecutive preset sliding time windows, the risk probabilities of each monitoring feature vector are arranged to obtain the risk probability time series of each candidate risk monitoring grid unit, so as to determine the safety risk origin grid unit according to the monitoring grid corresponding to the mutation point of the risk probability time series. Extracting the mechanical transmission characteristics from the monitoring data specifically includes: The risk type of the safety risk originating grid cell is determined, and a corresponding mechanical transmission index is matched according to the risk type; wherein, the mechanical transmission index includes: stress transmission coefficient, strain diffusion rate, displacement transmission attenuation rate, and load transmission path curvature; The spatiotemporal monitoring data sequence is filtered to obtain the specified monitoring data corresponding to the mechanical transmission index; Based on the specified monitoring data corresponding to the safety risk origin grid cell and the adjacent monitoring grid, the values ​​of each mechanical transmission index are determined; The values ​​of each of the aforementioned mechanical transmission indices are normalized to obtain the mechanical transmission characteristics corresponding to the grid cells from which the safety risks originate.

2. The construction safety monitoring method based on the Internet of Things according to claim 1, characterized in that, Based on the static sensing nodes deployed in the current pipeline construction area and the dynamic sensing nodes deployed on various mobile machines, the current pipeline construction area is spatially divided to obtain a monitoring grid, specifically including: Acquire the fixed monitoring performance information of static sensing nodes deployed in the current pipeline construction area, and the real-time monitoring performance information of dynamic sensing nodes deployed in various mobile machinery. Based on the fixed monitoring performance information of static sensor nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensor nodes deployed in various mobile machinery, spatial clustering is performed to divide the current pipeline construction area into a monitoring grid; wherein, the monitoring grid includes two layers: a static grid and a dynamic grid.

3. The construction safety monitoring method based on the Internet of Things according to claim 1, characterized in that, Based on the fixed monitoring performance information of static sensor nodes deployed in the current pipeline construction area and the real-time monitoring performance information of dynamic sensor nodes deployed on various mobile machinery, spatial clustering is performed to divide the current pipeline construction area into a monitoring grid, specifically including: Based on the fixed monitoring performance information of the static sensing nodes, determine the fixed monitoring location and monitoring range of each static sensing node; Based on the monitoring location and the monitoring range, the static sensing nodes are clustered to obtain the static grid cells of the current pipeline construction area; Based on the monitoring information of the dynamic sensing nodes, determine the position coordinates and mechanical operation limit range of each dynamic sensing node, and determine the dynamic monitoring coverage area corresponding to each dynamic sensing node based on the position coordinates and the mechanical operation limit range. The dynamic monitoring coverage area of ​​the same mobile machinery's dynamic sensing nodes within a preset time window is divided into dynamic grid units; wherein, the boundary of the dynamic grid unit is generated by fitting the movement trajectory of the mobile machinery. The static and dynamic grid units are mapped to a preset spatial coordinate system, a grid unit association table is established, the spatial overlap relationship between the dynamic and static grid units is obtained, and the monitoring grid corresponding to the current pipeline construction area is generated.

4. The construction safety monitoring method based on the Internet of Things according to claim 2, characterized in that, Simulate the security risk propagation path corresponding to each security risk originating grid cell, specifically including: Based on the spatial overlap relationship between static and dynamic grid units in the grid unit association table, each monitoring grid unit is taken as a node, the connection relationship between adjacent grid units is taken as an edge, and the weight of the edge is obtained based on the mechanical transmission characteristics between the grid unit where the safety risk originates and the adjacent grid units, so as to generate the risk spread topology network of the current pipeline construction area. Based on the characteristics of mechanical transmission, an initial risk transmission function is established, and the initial risk transmission function is modified according to the pipeline construction plan information of the current pipeline construction area to obtain the risk transmission function. Substitute the grid cells representing the origin of security risks into the risk transmission function to obtain the cumulative risk intensity of adjacent grid cells according to a preset period; If the risk accumulation intensity of the adjacent grid cell is determined to be greater than a preset risk threshold, then the adjacent grid cell is determined to be a risk propagation node. Based on the real-time monitoring performance information of the flowing machinery fed back by each dynamic grid cell, the node position and edge weight of the dynamic grid cell are updated. The risk accumulation intensity of adjacent grid cells is obtained iteratively based on the updated node position and edge weight to supplement and update the risk spread nodes. Based on the determined time corresponding to each security risk origin grid cell and each risk spread node, the security risk origin grid cells and each risk spread node are connected to obtain the security risk spread path corresponding to each security risk origin grid cell.

5. The construction safety monitoring method based on the Internet of Things according to claim 1, characterized in that, Based on the pipeline construction plan information for the current pipeline construction area and the safety risk propagation path, key risk grid cells are identified, specifically including: Key construction elements are extracted from the pipeline construction plan information. Based on the location information corresponding to the key construction elements and the monitoring grid units covered by each safety risk propagation path, risk propagation grid units that spatially overlap with the key construction elements are identified as candidate key risk grid units. Based on the construction schedule within the pipeline construction scheme information, determine the time sensitivity value of the construction activities corresponding to each candidate key risk grid unit; By combining the risk accumulation intensity of each risk propagation node in the security risk propagation path with the time sensitivity value of the corresponding candidate key risk grid unit, the comprehensive risk assessment value of each candidate key risk grid unit is determined. The comprehensive risk assessment value is compared with the preset key risk threshold. If the comprehensive risk assessment value is greater than the preset key risk threshold, the corresponding candidate key risk grid cell is determined as a key risk grid cell.

6. The construction safety monitoring method based on the Internet of Things according to claim 1, characterized in that, Early warning scheduling is performed on the construction management terminal of the key risk grid unit, specifically including: Based on the pre-set hierarchical response mechanism, the early warning instructions corresponding to the key risk grid units are determined, and the handling map of the key risk grid units is determined based on the spatial distribution characteristics of the key risk grid units. The warning instruction and the handling map are sent to the construction management terminal of the key risk grid unit to obtain feedback data from the construction management terminal; The response map is updated based on the feedback data to enable early warning and scheduling of the current pipeline construction area.

7. A construction safety monitoring device based on the Internet of Things, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-6.

8. A non-volatile storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are capable of performing the method described in any one of claims 1-6.

Images