Safety distance monitoring method and system for net rack and pipe truss construction

Abstract

The application relates to the technical field of data processing, and discloses a safety distance monitoring method and system for net rack and pipe truss construction. The method comprises the following steps: acquiring key node safety distance data, construction state data and environmental interference data, and integrating the data into a safety distance monitoring data set; performing abnormal screening and error compensation on the data set to generate a standardized data stream; analyzing the data stream to establish a deformation feature table and generate a deformation state report; positioning a dangerous area based on the report matching early warning conditions and outputting early warning information; determining an intervention node according to the early warning information and generating an adjustment instruction; and combining the adjustment instruction and historical data to establish an association network and generate a management knowledge base. The application realizes intelligent monitoring of the safety distance in the construction process of the net rack and the pipe truss, establishes an early warning mechanism through fusion analysis of multi-source data, and provides a scientific disposal scheme based on historical experience data, so that the accuracy and reliability of construction safety management are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and particularly relates to a safety distance monitoring method and system for net rack and pipe truss construction. BACKGROUND

[0002] In the existing net rack and pipe truss construction, safety distance monitoring mainly relies on manual inspection and fixed sensor data collection. Manual inspection obtains structural state information through field measurement, visual inspection and other methods; fixed sensors collect deformation data through displacement meters, strain gauges and other devices arranged at key nodes. These monitoring data are processed simply and used to judge the safety state of the structure. When an abnormality is found, the on-site management personnel decide the disposal scheme according to experience.

[0003] However, the existing monitoring method has many shortcomings. First, the data collection method is relatively single, which is difficult to fully reflect the real-time state of the net rack structure; second, the data processing process lacks systematicness, and it is difficult to effectively integrate multi-source information; third, the early warning mechanism is too simple, and problems are often discovered after they appear; finally, the formulation of disposal scheme is too dependent on personal experience, lacks data support, and it is difficult to guarantee the reliability of disposal effect. These problems seriously affect the safety management level of net rack and pipe truss construction. SUMMARY

[0004] The present application provides a safety distance monitoring method and system for net rack and pipe truss construction, which realizes intelligent monitoring of safety distance in the construction process of net rack and pipe truss, establishes an early warning mechanism through fusion analysis of multi-source data, and provides a scientific disposal scheme based on historical experience data, thereby improving the accuracy and reliability of construction safety management.

[0005] In a first aspect, the application provides a safety distance monitoring method for a grid and pipe truss construction, which comprises: integrating original data collected by a key node safety distance sensor, construction state data collected by a working condition identification sensor, and environmental interference data collected by an environmental parameter sensor into a grid safety distance monitoring original data set through a distributed data collection terminal; screening out abnormal data and performing error compensation based on the grid safety distance monitoring original data set to generate a standardized safety distance data stream; performing grid deformation feature analysis on the standardized safety distance data stream, and establishing a deformation correlation feature table according to node displacement data and working condition feature data to generate a grid structure deformation state evaluation report; matching a warning trigger condition based on the grid structure deformation state evaluation report, combining abnormal deformation mode identification to realize dangerous area positioning, and outputting a grid safety warning information package; determining a key intervention node according to a process influence evaluation matrix for the grid safety warning information package to generate a grid construction safety adjustment instruction; and establishing a safety event feature correlation network according to the grid construction safety adjustment instruction and historical safety event data to generate a grid construction safety management knowledge base.

[0006] In a second aspect, the application provides a safety distance monitoring method system for a grid and pipe truss construction, which comprises:

[0007] A collection module is configured to integrate original data collected by a key node safety distance sensor, construction state data collected by a working condition identification sensor, and environmental interference data collected by an environmental parameter sensor into a grid safety distance monitoring original data set through a distributed data collection terminal.

[0008] A screening module is configured to screen out abnormal data and perform error compensation based on the grid safety distance monitoring original data set to generate a standardized safety distance data stream.

[0009] A generation module is configured to perform grid deformation feature analysis on the standardized safety distance data stream, and establish a deformation correlation feature table according to node displacement data and working condition feature data to generate a grid structure deformation state evaluation report.

[0010] A positioning module is configured to match a warning trigger condition based on the grid structure deformation state evaluation report, combine abnormal deformation mode identification to realize dangerous area positioning, and output a grid safety warning information package.

[0011] An adjustment module is configured to determine a key intervention node according to a process influence evaluation matrix for the grid safety warning information package to generate a grid construction safety adjustment instruction.

[0012] The management module is used for establishing a safety event feature correlation network according to the net rack construction safety adjustment instruction and historical safety event data, and generating a net rack construction safety management knowledge base.

[0013] In the technical scheme provided in the application, the original data collected by the key node safety distance sensor, the construction state data collected by the working condition identification sensor and the environmental interference data collected by the environmental parameter sensor are integrated to construct a net rack safety distance monitoring original data set, the collaborative collection and fusion processing of multi-source data are realized, the problem of incomplete information of a single data source is overcome, the real-time performance and reliability of data collection are improved through the setting of the distributed data collection terminal, the abnormal data of the net rack safety distance monitoring original data set is screened out and error compensation is performed to generate a standardized safety distance data stream, the influence of environmental interference and random error is effectively eliminated, and the data quality is improved, the standardized safety distance data stream is combined with the working condition feature data to perform deformation feature analysis, a deformation correlation feature table is established and a net rack structure deformation state evaluation report is generated, the accurate evaluation of the structure deformation state is realized, the early warning trigger mechanism is established based on the net rack structure deformation state evaluation report, the accurate positioning of the dangerous area is realized through abnormal deformation mode identification, and the output net rack safety early warning information package provides a reliable basis for construction management, the key intervention nodes are determined in combination with the process influence evaluation matrix, the generated net rack construction safety adjustment instruction has strong pertinence and operability, the safety event feature correlation network is established and the net rack construction safety management knowledge base is generated, the accumulation and inheritance of construction experience are realized, and a reference basis is provided for subsequent similar projects. The whole scheme adopts an artificial intelligence algorithm to process and analyze multi-source data, fully gives play to the advantages of deep learning in pattern recognition and feature extraction, realizes the intelligentization of the whole process from data collection, processing, analysis to decision support, and significantly improves the scientificity and reliability of net rack and pipe truss construction safety monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical scheme of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0015] Figure 1 An embodiment schematic diagram of the safety distance monitoring method of the net rack and pipe truss construction in the embodiment of the application;

[0016] Figure 2 A flowchart schematic diagram of the integrated net rack safety distance monitoring original data set in the embodiment of the application;

[0017] Figure 3An embodiment of the safety distance monitoring method and system for the construction of the grid and pipe truss in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a safety distance monitoring method and system for the construction of the grid and pipe truss. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0019] For the convenience of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 The safety distance monitoring method for the construction of the grid and pipe truss in the embodiments of the present application includes one embodiment:

[0020] Step S101, the original data collected by the key node safety distance sensor, the construction state data collected by the working condition identification sensor and the environmental interference data collected by the environmental parameter sensor are integrated into a grid safety distance monitoring original data set through a distributed data collection terminal;

[0021] Step S102, according to the grid safety distance monitoring original data set, abnormal data is screened out and error compensation is performed to generate a standardized safety distance data stream;

[0022] Step S103, the standardized safety distance data stream is analyzed for grid deformation characteristics, and a deformation correlation feature table is established according to the node displacement data and the working condition characteristic data to generate a grid structure deformation state evaluation report;

[0023] Step S104, based on the grid structure deformation state evaluation report, the pre-warning trigger condition is matched, the dangerous area is located by combining the abnormal deformation mode recognition, and a grid safety pre-warning information package is output;

[0024] Step S105, the key intervention nodes are determined according to the process influence evaluation matrix for the grid safety pre-warning information package to generate a grid construction safety adjustment instruction;

[0025] Step S106, according to the grid construction safety adjustment instruction and the historical safety event data, a safety event feature correlation network is established to generate a grid construction safety management knowledge base.

[0026] It can be understood that the execution subject of the present application can be a net rack and pipe truss construction safety distance monitoring method system, and can also be a terminal or a server, and the specific place is not limited. The server is taken as an example for description in the embodiment of the present application.

[0027] Specifically, data is collected through a distributed sensor network. The key node safety distance sensor collects real-time distance change data between nodes in a three-dimensional space, with a sampling frequency of 10 Hz, and the data contains node number, time stamp, and relative displacement values in X / Y / Z directions. The working condition recognition sensor collects data such as the position of mechanical equipment, the distribution of workers, and the state of material stacking in the construction site, forming a construction state data packet. The environmental parameter sensor monitors environmental factors such as temperature, humidity, and wind speed, generating environmental interference data. The distributed data collection terminal synchronizes the time and registers the space of the three types of data, and integrates to form a net rack safety distance monitoring original data set.

[0028] The net rack safety distance monitoring original data set is subjected to data quality analysis, and a threshold range is set for the safety distance data. Data points outside the reasonable range are marked as abnormal. For measurement errors caused by temperature changes, compensation correction is made based on the temperature-deformation relationship curve. Random errors caused by environmental factors such as humidity and wind speed are eliminated through data smoothing. After abnormal value screening and error compensation, a standardized safety distance data stream is formed. The standardized safety distance data stream is input into the net rack deformation feature analysis module to extract the time sequence change characteristics of node displacement, including displacement amplitude, deformation rate, acceleration, etc. Combined with the working condition feature data, the deformation characteristics of different construction stages are analyzed, such as dynamic deformation in the hoisting process and thermal deformation in the welding process. The corresponding relationship between node deformation and construction working conditions is established, and a deformation correlation feature table is formed. Based on the statistical analysis of deformation data, a net rack structure deformation state evaluation report is generated.

[0029] The deformation data in the deformation state evaluation report is compared with the preset safety threshold, and a warning is triggered when the threshold is exceeded. The abnormal deformation mode recognition module analyzes the spatial distribution characteristics of the deformation to locate the core position and the influence range of the abnormal deformation area. The warning level, the dangerous area range, the deformation development trend, and other information are packaged to form a net rack safety warning information package. The net rack safety warning information package is input into the construction process optimization module to analyze the influence degree of each process on the structure deformation based on the process influence evaluation matrix. The process influence evaluation matrix contains the sensitive coefficients of hoisting, welding, reinforcement, and other processes on node deformation. The key nodes that need to be intervened first are determined, and a construction adjustment scheme is generated to form a net rack construction safety adjustment instruction.

[0030] Construction safety adjustment instructions are associated with historical safety event data to extract common characteristics and rules. Historical event data includes event type, influencing factors, disposal measures, and effect evaluation information. Through data mining, the association network between safety events is established to identify high-risk points and key influencing factors. Standardized construction safety management procedures are formed and a network construction safety management knowledge base is established.

[0031] For example, in the construction of a large exhibition center steel structure net rack, the roof net rack has a span of 120 meters and a height of 30 meters, which is composed of 3600 nodes and 12000 rod members. During construction, the safety distance monitoring system monitors key nodes in real time. When it is detected that the distance between adjacent nodes N365 and N366 increases from the design value of 1500mm to 1580mm within 10 minutes during the hoisting of No. 3 main truss, it exceeds the safety threshold. The system immediately analyzes the deformation data of the surrounding nodes and finds that the deformation area presents a radial expansion trend. Combined with the analysis of the working condition data, it is found that the main truss is being hoisted and the 50-ton crawler crane is parked 12 meters away from the deformation center. The system automatically generates a warning message, suggests suspending the hoisting operation, and provides a temporary support reinforcement scheme for the truss. After the construction personnel take measures according to the system's suggestions, the node deformation is effectively controlled, and the distance between adjacent nodes stabilizes at 1520mm. The disposal experience of this warning process is extracted by the system and stored in the knowledge base to guide the construction management of subsequent similar working conditions.

[0032] In this embodiment, a raw dataset for monitoring the safety distance of the grid structure is constructed by integrating the raw data collected by the safety distance sensor at key nodes, the construction status data collected by the working condition identification sensor, and the environmental interference data collected by the environmental parameter sensor. This achieves collaborative acquisition and fusion processing of multi-source data, overcoming the problem of incomplete information from a single data source. The use of distributed data acquisition terminals improves the real-time performance and reliability of data acquisition. Abnormal data is filtered and error compensation is performed on the raw dataset for monitoring the safety distance of the grid structure to generate a standardized safety distance data stream, effectively eliminating the influence of environmental interference and random errors, and improving data quality. The standardized safety distance data stream is then integrated with the construction data. By combining characteristic data with deformation feature analysis, a deformation correlation feature table is established, and a deformation status assessment report for the space frame structure is generated, achieving accurate assessment of the structural deformation status. Based on the space frame structure deformation status assessment report, an early warning triggering mechanism is established. Accurate location of hazardous areas is achieved through abnormal deformation pattern recognition, and the output space frame safety early warning information package provides a reliable basis for construction management. By combining the process impact assessment matrix to determine key intervention nodes, the generated space frame construction safety adjustment instructions are highly targeted and operable. By establishing a safety event feature correlation network and generating a space frame construction safety management knowledge base, construction experience is accumulated and passed on, providing a reference for subsequent similar projects. The entire solution uses artificial intelligence algorithms to process and analyze multi-source data, fully leveraging the advantages of deep learning in pattern recognition and feature extraction. It achieves intelligent processing throughout the entire process from data acquisition, processing, and analysis to decision support, significantly improving the scientific rigor and reliability of space frame and tubular truss construction safety monitoring.

[0033] In one specific embodiment, the process of performing step S101 may specifically include the following steps:

[0034] (1) Convert the node three-dimensional coordinate data collected by the key node safety distance sensor within the preset sampling period into a raw data set of safety distance;

[0035] (2) Integrate the construction machinery location data, worker distribution data and material stacking status data collected by the working condition identification sensor into a construction status feature data group;

[0036] (3) The temperature field data, humidity field data and vibration field data collected by the environmental parameter sensors are fused into an environmental disturbance characteristic data set;

[0037] (4) Perform timestamp matching on the original data set of safety distance, the data set of construction status characteristics, and the data set of environmental disturbance characteristics to generate a time-series correlation data table;

[0038] (5) Spatial mapping of the time-series correlation data table according to the node number to establish a spatial relationship matrix for monitoring the safe distance of the network nodes;

[0039] (6) According to the spatial relationship matrix of the net node safety distance monitoring and the time sequence correlation data table, the data is integrated in time and space dimensions to generate the net safety distance monitoring original data set.

[0040] Specifically, as shown in Figure 2 , it is a process diagram for integrating the net safety distance monitoring original data set in the embodiment of the application. In the data collection stage, the process of converting the three-dimensional coordinate data collected by the key node safety distance sensor into the safety distance original data set, the process of integrating the construction machinery position data, the work personnel distribution data and the material stacking state data collected by the working condition recognition sensor into the construction state feature data set, and the process of fusing the temperature field data, the humidity field data and the vibration field data collected by the environmental parameter sensor into the environmental interference feature data set are shown. In the data processing stage, the process of generating the time sequence correlation data table by time stamp matching the safety distance original data set, the construction state feature data set and the environmental interference feature data set, and the process of establishing the spatial relationship matrix of the net node safety distance monitoring by spatial mapping the time sequence correlation data table according to the node number are shown. In the data integration stage, the process of integrating the data in time and space dimensions according to the spatial relationship matrix of the net node safety distance monitoring and the time sequence correlation data table to generate the net safety distance monitoring original data set is shown.

[0041] The data collected by the key node safety distance sensor is converted and processed. The key node safety distance sensor collects the three-dimensional coordinate data of each node in the preset 100ms sampling period, including node number, X / Y / Z coordinate value and time stamp. The collected three-dimensional coordinate data is converted and processed, the actual distance between adjacent nodes is calculated, and the calculated distance data is organized according to node pairs to form the safety distance original data set.

[0042] The working condition recognition sensor arranged on the construction site continuously tracks and records the real-time position information of the construction machinery, obtains the two-dimensional coordinates of the mechanical equipment through GPS positioning, and obtains the working height of the equipment in combination with the height sensor. The working condition recognition sensor also collects the spatial distribution of the workers through infrared imaging, records the number of personnel and the activity range in each work area. For the material stacking state, the gravity sensor and displacement sensor are used to record the load distribution and occupied area of the stacking yard. These data are organized according to the time and space dimensions, and are integrated into a construction state feature data set. The environmental parameter sensor network is composed of temperature sensors, humidity sensors and vibration sensors. The temperature sensors are arranged in a 5m×5m grid in the construction space to collect temperature field distribution data. The humidity sensors are arranged at the same points as the temperature sensors to obtain the spatial humidity distribution. The vibration sensors are arranged at the key nodes of the net rack to record the structure vibration acceleration. The three types of environmental parameter data are processed by spatial interpolation to generate continuous environmental field distribution data, which are fused into an environmental interference feature data set.

[0043] The above three groups of data are first timestamped. The sampling period of the safety distance original data set is 100ms, the sampling period of the construction state feature data set is 1s, and the sampling period of the environmental interference feature data set is 10s. Through the time window sliding method, the three groups of data are mapped to a unified time reference. The data in each time window is synthesized into a record by weighted average method, generating a time series correlation data table.

[0044] For the spatial mapping process of the time series correlation data table, the following mathematical model is used:

[0045] ;

[0046] Among them: represents the spatial relationship matrix between node i and node j; represents the kth safety distance parameter; represents the pth working condition influence factor; represents the qth environmental interference factor; , , are the weight coefficients of the corresponding parameters; , , are the number of safety distance parameters, working condition influence factors and environmental interference factors, respectively.

[0047] The spatial relationship matrix of the net rack node safety distance monitoring and the time sequence correlation data table are combined, and a four-dimensional data structure is constructed according to the spatial position relationship and the time sequence change characteristics of the node. In the spatial dimension, the three-dimensional coordinate information and the mutual relationship of the node are included, and in the time dimension, the change process of various types of monitoring data is included, forming a complete net rack safety distance monitoring original data set.

[0048] For example, in the construction of a certain stadium net rack structure, the net rack is composed of 2000 nodes, and 500 key monitoring points are set. During the hoisting process of the main truss, the safety distance sensor of the key node P156 records the distance data of the adjacent nodes P157 and P158, the 80-ton crawler crane in the construction site is performing lifting operation, and the operating personnel are distributed around the hoisting area. The environmental parameters show that the temperature of the hoisting area is 28°C, the relative humidity is 75%, and the measured structural vibration acceleration is 0.15g.

[0049] In a specific embodiment, the process of performing step S102 can specifically include the following steps:

[0050] (1) The net rack safety distance monitoring original data set is divided into safety distance monitoring data groups according to the safety distance relationship of adjacent nodes;

[0051] (2) Based on the safety distance monitoring data group, a node safety distance change curve is constructed, and a safety distance trend data table is generated;

[0052] (3) According to the safety distance trend data table, a mutation point is detected, an abnormal data point is marked, and a safety distance abnormal data record is formed;

[0053] (4) The safety distance abnormal data record and the environmental interference data are associated for correlation analysis, the abnormal characteristics caused by interference are extracted, and an environmental interference influence evaluation table is generated;

[0054] (5) According to the environmental interference influence evaluation table, the net rack safety distance monitoring original data set is filtered to obtain a net rack safety distance effective data set;

[0055] (6) The net rack safety distance effective data set is normalized according to the standardization processing procedure to generate a standardized safety distance data stream.

[0056] Specifically, the node relationship of the truss safety distance monitoring original data set is divided. According to the topological relationship of the truss structure, a single node is taken as the center to determine the nearby node group directly connected around it. The judgment standard of the nearby node is based on the physical connection relationship between nodes, that is, the nodes directly connected through the rod are defined as the nearby nodes. The distance data between each node and its nearby nodes are extracted and grouped to form a safety distance monitoring data group in node units. After obtaining the safety distance monitoring data group, each group of data is arranged in time sequence. Based on the time series analysis method, the distance data between each pair of nearby nodes is curve-fitted to obtain the trend curve of the distance between nodes changing with time. The trend curve reflects the change law of the relative displacement between nodes, and contains characteristic information such as distance change rate and acceleration. The trend curves of all node pairs and their characteristic parameters are arranged in table form to generate a safety distance trend data table. The safety distance trend data table is subjected to mutation point detection, and a time series data anomaly detection algorithm is used to identify abnormal points in the distance change. The judgment basis of the abnormal points includes that the distance change rate exceeds the preset threshold, the acceleration suddenly changes, and the statistical characteristics deviate significantly from the historical data. The marked abnormal data points are recorded in time sequence and spatial position to form a safety distance abnormal data record.

[0057] The safety distance abnormal data record is analyzed for correlation with the environmental interference data collected by the environmental parameter sensor. The environmental interference data includes temperature, humidity, vibration and other parameters of the measurement point position. Through correlation analysis method, the correlation between the environmental parameters at the time when the abnormal data point appears and the abnormal degree is calculated. The analysis results are classified and arranged according to the environmental factor category and the influence degree to generate an environmental interference influence evaluation table. According to the analysis results in the environmental interference influence evaluation table, the data in the truss safety distance monitoring original data set significantly affected by environmental factors is filtered. For different types of environmental interference, the corresponding data correction method is used: thermal compensation correction is performed for the deformation caused by temperature, smoothing processing is used for the fluctuation caused by vibration, drift correction is used for the influence of humidity, etc. The data filtered by environmental interference constitutes the truss safety distance effective data set.

[0058] The truss safety distance effective data set is subjected to standardization processing to convert different dimensional data to a unified scale space. The standardization processing includes two steps of data normalization and dimensionless. First, the data is subjected to zero-mean standardization processing, and then normalized mapping is performed according to the preset data range to finally generate standardized safety distance data stream.

[0059] For example, in the construction of a large sports stadium grid structure, the main grid is composed of 3000 nodes, and 1000 key nodes are selected for safety distance monitoring. For each node, first identify its directly connected adjacent nodes, with an average of 6 adjacent nodes per node, forming a node safety distance monitoring data set. During the hoisting process of the main truss, the distance between key node N245 of the second span of the main truss and its adjacent node N246 changes within 1 hour, and the distance value gradually increases from the designed distance of 1200 mm to 1245 mm. After mutation point detection, it is found that the acceleration mutation occurs when the distance reaches 1230 mm. Environmental data shows that the temperature in this area reaches 36℃ when the mutation occurs, and welding is being carried out, resulting in local thermal deformation. Through correlation analysis, it is determined that this is a temporary deformation caused by welding heat effect, and the node spacing returns to normal after cooling.

[0060] In a specific embodiment, the process of performing step S103 can specifically include the following steps:

[0061] (1) Establish a node safety distance monitoring network based on the standardized safety distance data stream and the grid topology structure, and output a spatial monitoring point group distribution matrix;

[0062] (2) Construct a deformation gradient field along the main support direction of the grid to form a grid deformation measurement data set;

[0063] (3) Statistically analyze the node deformation peak interval with the help of the grid deformation measurement data set, and generate a working condition-deformation coupling data package combined with working condition characteristic data;

[0064] (4) Based on the working condition-deformation coupling data package, extract the key deformation node link of the grid, and construct a deformation propagation path map;

[0065] (5) Analyze the node deformation evolution law through the deformation propagation path map, and draw a deformation correlation characteristic table;

[0066] (6) Fuse the deformation correlation characteristic table with the overall stability index of the grid to output a grid structure deformation state evaluation report.

[0067] Specifically, all monitoring nodes are coded according to spatial position, and a connection relationship matrix between nodes is established, including the spatial coordinates of the nodes and the adjacent node information. The spatial distribution of the surrounding monitoring points of each node is analyzed, the relative position and connection relationship between nodes are calculated, and a spatial monitoring point group distribution matrix is formed.

[0068] When constructing the deformation gradient field along the main support direction of the grid, the following calculation method is used:

[0069] ;

[0070] wherein: represents the deformation gradient field in three-dimensional space; represents the horizontal displacement of the i-th node; represents the vertical displacement of the j-th node; , is a weight coefficient; , represents the spatial coordinates in the horizontal and vertical directions, respectively; , are the number of horizontal and vertical monitoring points, respectively.

[0071] Based on the deformation gradient field data calculated, combined with the measured displacement values of the nodes, the net deformation measurement data set is formed.

[0072] When performing node deformation peak value statistics on the net deformation measurement data set, the following model is used:

[0073] ;

[0074] wherein: represents the deformation peak value at time t; represents the k-th working condition characteristic parameter; represents the l-th deformation parameter; , is a weight coefficient; represents the coupling operator; , are the number of working condition characteristics and deformation parameters, respectively.

[0075] When extracting the key deformation node link of the net, the following calculation method is used:

[0076] ;

[0077] wherein: represents the deformation propagation path strength; represents the deformation response strength of the u-th node; represents the w-th propagation factor; , is a weight coefficient; , The number of key nodes and the number of propagation factors, respectively. The deformation peak interval data and the working condition characteristic data are subjected to time sequence matching and correlation analysis. The analysis process comprehensively considers the influence of working condition factors such as construction process, equipment arrangement, and load distribution on node deformation, and records the deformation response characteristics under different working conditions. The deformation data corresponding to each working condition are assigned with time stamps and spatial identifiers, facilitating the tracking of the deformation development process. In the construction of the deformation propagation path map, the diffusion law of deformation in the space truss structure is focused on. By analyzing the deformation transmission relationship between adjacent nodes, the main and secondary paths of deformation propagation are identified. Key parameters such as propagation speed and attenuation characteristics are marked for each propagation path, and a propagation path map of the net structure is drawn. The map clearly shows the transmission direction and influence range of deformation in the space truss structure.

[0078] For the data in the deformation propagation path map, the spatio-temporal evolution law of node deformation is analyzed. The characteristics such as the starting position, propagation direction, and influence range of deformation are recorded, and these characteristics are associated with the spatial position relationship of the nodes. By comparing and analyzing the deformation data in multiple time windows, the regularity characteristics of deformation development are summarized, and a deformation correlation characteristic table is drawn. In the generation process of the space truss structure deformation state evaluation report, the deformation correlation characteristic table needs to be integrated with the overall stability indicators of the space truss. The overall stability indicators include node displacement limit value, structure deformation allowable value, support reaction force, etc. By comprehensively evaluating the deformation development trend and the bearing capacity of the structure, detailed state evaluation conclusions are formed.

[0079] For example, in the construction of a space truss structure of an exhibition hall, the space truss has a span of 80 meters and is composed of 2400 nodes in a grid structure. During the hoisting construction stage of the main truss, real-time monitoring found that the displacement value of node C156 in region C suddenly increased. Analysis of the deformation data of the surrounding nodes found that the deformation region centered on C156 showed a radial expansion trend, and the deformation gradient field showed that the vertical deformation rate of this region was significantly higher than that of other regions. Combined with the working condition data analysis, it was shown that the roof panel installation was being carried out at this time, and a material storage yard was arranged near the deformation center. Through deformation propagation path analysis, it was found that the deformation started from node C156 and spread along the main truss direction to both sides, affecting about 20 surrounding nodes. According to the deformation correlation characteristic table, the deformation rate showed a clear positive correlation with the material pile load. The final state evaluation report pointed out the cause of the deformation and made optimization suggestions for the arrangement of material stacking.

[0080] In a specific embodiment, the process of performing step S104 can specifically include the following steps:

[0081] (1) Subdivide the deformation state of the space truss construction hoisting area, welding reinforcement area, and component installation area in the space truss structure deformation state evaluation report to generate partition monitoring and early warning indicators;

[0082] (2) Analyze the deformation characteristics of nodes caused by the movement of large construction equipment using partition monitoring and early warning indicators to form equipment construction interference evaluation data;

[0083] (3) Correlate and analyze the equipment construction interference evaluation data with the stability of adjacent nodes to establish a list of construction condition influence coefficients;

[0084] (4) Extract the stress variation law of the net rack node from the construction condition influence coefficient list to mark the high stress concentration construction area;

[0085] (5) According to the deformation development trend of the high stress concentration construction area, draw a net rack construction danger operation area early warning distribution map;

[0086] (6) Set graded early warning thresholds according to the net rack construction danger operation area early warning distribution map and output the net rack safety early warning information package.

[0087] Specifically, the deformation peak interval data and the working condition characteristic data are time series matched and correlated. The analysis process considers the influence of construction process, equipment arrangement, load distribution and other working condition factors on node deformation, and records the deformation response characteristics under different working conditions. The deformation data corresponding to each working condition is assigned a time stamp and a spatial identifier. In the construction of the deformation propagation path map, the diffusion law of deformation in the net rack structure is focused on. By analyzing the deformation transmission relationship between adjacent nodes, the main and secondary paths of deformation propagation are identified. Key parameters such as propagation speed and attenuation characteristics are marked for each propagation path, and a net-like structure propagation path map is drawn. This map clearly shows the transmission direction and influence range of deformation in the net rack structure.

[0088] For the data in the deformation propagation path map, the spatio-temporal evolution law of node deformation is analyzed. The characteristics of deformation occurrence, propagation direction, influence range, etc. are recorded and associated with the spatial position relationship of the node. By comparing and analyzing the deformation data in multiple time windows, the regularity characteristics of deformation development are summarized, and a deformation correlation characteristic table is drawn. In the generation process of the net rack structure deformation state evaluation report, the deformation correlation characteristic table needs to be integrated with the overall stability indicators of the net rack. The overall stability indicators include node displacement limit value, structure deformation allowable value, support reaction force and other parameters. By comprehensively evaluating the deformation development trend and the structure bearing capacity, a detailed state evaluation conclusion is formed.

[0089] For example, in the construction of a netted frame structure in an exhibition hall, the netted frame span is 80 meters, and the grid structure is composed of 2400 nodes. During the hoisting construction stage of the main truss, real-time monitoring found that the displacement value of node C156 in area C suddenly increased. By analyzing the deformation data of the surrounding nodes, it was found that the deformation area centered on C156 showed a radial expansion trend, and the deformation gradient field showed that the vertical deformation rate of this area was significantly higher than that of other areas. Combined with the working condition data analysis, it was shown that the roof panel installation was being carried out at this time, and a material storage yard was arranged near the deformation center. Through the deformation propagation path analysis, it was found that the deformation started from node C156 and spread along the main truss direction to both sides, affecting about 20 nodes around. According to the deformation correlation characteristic table, the deformation rate showed a significant positive correlation with the material pile load. The final state evaluation report pointed out the cause of the deformation and made optimization suggestions for the arrangement of material stacking.

[0090] In an embodiment, the process of step S105 can specifically include the following steps:

[0091] (1) The netted frame safety warning information package is divided into node deformation data package, process interference data package, and safety limit value data package, and a classified warning factor table is generated;

[0092] (2) The force state of the netted frame support points, connection nodes, and main rod members is analyzed according to the classified warning factor table, and a process influence evaluation matrix is formed;

[0093] (3) High-risk construction process combinations are selected from the process influence evaluation matrix, and a netted frame construction intervention list is sorted out;

[0094] (4) The hoisting process, welding process, and reinforcement process are checked for conflicts according to the netted frame construction intervention list, and the node intervention priority is marked;

[0095] (5) The section where the hazard source is located is divided into an emergency disposal area, a key control area, and a conventional monitoring area according to the node intervention priority, and a netted frame key intervention node table is output;

[0096] (6) The netted frame key intervention node table is converted into specific construction control measures, and a netted frame construction safety adjustment instruction is generated.

[0097] Specifically, the data is divided into three categories according to the nature: the node deformation data packet records the displacement value, deformation rate and acceleration of each monitoring point; the process interference data packet contains the construction equipment position, operation personnel distribution and material stacking status; the safety limit value data packet stores the pre-warning threshold of various parameters. The three types of data are classified and arranged, and a pre-warning factor table is established to clearly define the data source and judgment standard corresponding to each pre-warning trigger condition. When analyzing the stress state of the grid structure according to the classified pre-warning factor table, focus on three types of key components: support points located at the connection between the grid and the foundation, bearing the load transfer of the overall structure; connecting nodes are the intersection of members, responsible for transferring internal forces; main members are the main load-bearing components. For these three types of components, analyze their stress changes under different construction processes, record mechanical parameters such as stress and deformation, and form a process influence evaluation matrix. This matrix reflects the influence degree of various construction processes on the stress state of the structure.

[0098] From the process influence evaluation matrix, extract the process combination with larger influence coefficient, and identify the high-risk construction links. Mainly focus on the dynamic load in the hoisting process, the thermal stress in the welding process, and the stress change of the support system, etc. Organize these high-risk processes and their influence range, duration, etc. into a grid construction intervention list. This list records in detail the construction links that need to be focused on and the corresponding monitoring requirements. According to the grid construction intervention list, analyze the process conflicts, and focus on checking the mutual influence between the hoisting process, welding process and reinforcement process. The hoisting process involves the movement of large equipment and the installation of components, which needs to ensure the operation space; the welding process produces local high temperature, affecting the surrounding area; the reinforcement process needs to consider the coordination with the original structure. Check the conflicts in time and space dimensions for these processes, and determine the priority of node intervention according to the conflict degree and risk level.

[0099] Based on the priority of node intervention, divide the construction area into safety levels: the emergency treatment area is the area where the deformation or stress has exceeded the safety limit value, and immediate intervention measures need to be taken; the key control area is the area close to the pre-warning value, which needs to be strengthened monitoring and prevention; the normal monitoring area is the area in normal state, which needs to be kept daily monitoring. According to this zoning method, determine the key intervention nodes and form a grid key intervention node table. When converting the grid key intervention node table into specific construction control measures, formulate corresponding disposal schemes for different areas and different risk levels. Including adjusting the construction sequence, optimizing the equipment layout, strengthening the local support, etc. Specific measures to form detailed grid construction safety adjustment instructions. These instructions clearly specify the execution steps, time nodes and quality requirements of each measure.

[0100] For example, in the construction of a certain airport terminal space truss structure, during the installation process in the main truss span area, it was found through monitoring data that the A12 node and its surrounding area were abnormal. Analysis of the early warning information found that the node deformation value in this area reached 80% of the design value, and the deformation rate showed an accelerating trend. At the same time, the process data showed that the roof panel installation was being carried out in this area, and a 150-ton crawler crane was moving into position. After inputting these information into the process influence evaluation system, it was identified that the superposition effect of hoisting process and roof construction caused local overload. Through process conflict checking, it was determined that the load distribution problem around the A12 node needed to be prioritized. According to the intervention priority, the area was divided into an emergency treatment zone, the roof panel installation work was suspended, the hoisting path was adjusted, and temporary supports were added to the key stressed nodes. These measures were issued to the construction team through construction safety adjustment instructions.

[0101] In a specific embodiment, the process of performing step S106 can specifically include the following steps:

[0102] (1) Extract the construction process control focus, intervention measure requirement, and safety limit range from the space truss construction safety adjustment instruction to form a construction control experience data set;

[0103] (2) Organize the space truss hoisting failures, node instability conditions, and support deformation records in the historical safety event data to establish a construction risk case library;

[0104] (3) Map the construction control experience data set and the construction risk case library to generate a set of space truss construction emergency disposal schemes;

[0105] (4) With the help of the set of space truss construction emergency disposal schemes, classify the node instability types, deformation overrun reasons, and environmental interference factors in different construction stages, and organize the experience knowledge item table;

[0106] (5) Based on the experience knowledge item table, establish the association relationship between construction accident prevention measures, emergency intervention means, and disposal effect evaluation to form a safety event feature association network;

[0107] (6) Summarize the management points, technical points, and operation points in the safety event feature association network to generate a space truss construction safety management knowledge base.

[0108] Specifically, the data of the net rack construction safety adjustment instruction is extracted. By analyzing the adjustment instruction text, the construction process control key points are extracted, including the monitoring parameters, early warning threshold, intervention opportunity and other information of each node; the intervention measure requirements are extracted, including the process adjustment scheme, equipment arrangement requirements, personnel configuration and other contents; the safety limit value range is extracted, including the node displacement limit value, deformation rate limit value, stress limit value and other parameters. The extracted data is classified and arranged according to the process type, intervention type and limit value type, forming a construction control experience data set. The historical safety event data is sorted and classified, focusing on three typical problems: the net rack hoisting failure data includes improper equipment arrangement, hoisting path conflict, uneven load distribution and other problems; the node instability data records the node connection loosening, welding deformation, support failure and other problems; the support deformation record includes temporary support deformation, permanent support settlement, foundation displacement and other conditions. The causes, development process and disposal methods of each type of problem are recorded in detail to establish a structured construction risk case library.

[0109] The construction control experience data set and the construction risk case library are associated and matched. First, the data is preliminarily screened according to the process type, and the experience data and risk cases under similar processes are paired. Then, scene similarity analysis is performed according to construction environment, structure characteristics, construction conditions and other factors to find the closest historical case to the current construction situation. Through this mapping relationship, the applicable disposal scheme is extracted to form a net rack construction emergency disposal scheme set. Based on the net rack construction emergency disposal scheme set, various problems occurring in the construction process are systematically classified. For node instability type, analyze its performance characteristics in different construction stages, such as dynamic instability in hoisting stage, thermal deformation instability in welding stage, fatigue instability in use stage, etc. For deformation overrun reasons, summarize typical reasons such as load overrun, insufficient support, poor node connection, etc. Environmental interference factors include temperature effect, wind load influence, foundation settlement, etc. Organize these analysis results into experience knowledge item table.

[0110] According to the experience knowledge item table, the problem-measure-effect association network is established. For each type of construction accident, analyze its corresponding preventive measures such as strengthening monitoring, optimizing process, supplementing support, etc.; corresponding emergency intervention means such as local reinforcement, load dispersion, emergency support, etc.; and corresponding disposal effect evaluation indexes such as deformation recovery degree, structure stability improvement, etc. Through the analysis of these association relationships, a complete safety event characteristic association network is formed. The safety event characteristic association network is knowledge refined and summarized. From the management level, the construction organization, personnel configuration, quality control and other management points are refined; from the technical level, the monitoring arrangement, early warning setting, intervention scheme and other technical points are summarized; from the operation level, the process connection, equipment operation, emergency disposal and other operation points are summarized. These contents are systematically arranged to form a net rack construction safety management knowledge base.

[0111] For example, during the construction of a large stadium's steel structure space frame, abnormal deformation was detected in the node group of area B during the hoisting of the main truss. A review of historical case studies revealed that similar situations had previously resulted in excessive localized deformation due to improper placement of hoisting equipment. Comparing the current construction conditions, a stress inconsistency was found between the location of the large lifting equipment and the support system. Based on past experience, the hoisting equipment position was immediately adjusted, and temporary support structures were added. During the process, a deviation from the planned welding sequence was also discovered, and the procedures were promptly optimized and adjusted.

[0112] The above describes the method for monitoring the safety distance during the construction of space frames and tubular trusses in this application. The following describes the system of the method for monitoring the safety distance during the construction of space frames and tubular trusses in this application. Please refer to [link to relevant documentation]. Figure 3 One embodiment of the safety distance monitoring method system for space frame and tubular truss construction in this application includes:

[0113] The data acquisition module 201 is used to integrate the raw data collected by the safety distance sensor at key nodes, the construction status data collected by the working condition identification sensor, and the environmental interference data collected by the environmental parameter sensor into a raw dataset for monitoring the safety distance of the grid structure through a distributed data acquisition terminal.

[0114] The screening module 202 is used to screen out abnormal data and perform error compensation based on the original dataset of the safety distance monitoring of the grid structure, and generate a standardized safety distance data stream.

[0115] The generation module 203 is used to perform space frame deformation characteristic analysis on the standardized safety distance data stream, and to establish a deformation correlation characteristic table based on the node displacement data and working condition characteristic data to generate a space frame structure deformation state assessment report.

[0116] The positioning module 204 is used to match the early warning triggering conditions based on the deformation state assessment report of the space frame structure, combine abnormal deformation pattern recognition to locate dangerous areas, and output a space frame safety early warning information package.

[0117] Adjustment module 205 is used to determine key intervention nodes based on the process impact assessment matrix of the space frame safety early warning information package and generate space frame construction safety adjustment instructions;

[0118] The management module 206 is used to establish a safety event feature association network and generate a knowledge base for safety management of space frame construction based on the space frame construction safety adjustment instructions and historical safety event data.

[0119] Through the cooperation of the above-mentioned components, the original data collected by the key node safety distance sensor, the construction state data collected by the working condition identification sensor and the environmental interference data collected by the environmental parameter sensor are integrated to construct a net frame safety distance monitoring original data set, realize the collaborative collection and fusion processing of multi-source data, overcome the problem of incomplete information of single data source, improve the real-time and reliability of data collection through the setting of distributed data collection terminal; the net frame safety distance monitoring original data set is screened for abnormal data and error compensation to generate standardized safety distance data stream, effectively eliminating the influence of environmental interference and random error and improving the data quality; the standardized safety distance data stream is combined with the working condition characteristic data for deformation feature analysis, a deformation correlation feature table is established and a net frame structure deformation state evaluation report is generated to realize accurate evaluation of the structure deformation state; an early warning trigger mechanism is established based on the net frame structure deformation state evaluation report, the precise positioning of the dangerous area is realized through abnormal deformation mode identification, and the output net frame safety early warning information package provides a reliable basis for construction management; the key intervention nodes are determined in combination with the process influence evaluation matrix, and the generated net frame construction safety adjustment instruction has strong pertinence and operability; the safety event feature correlation network is established and the net frame construction safety management knowledge base is generated to realize the accumulation and inheritance of construction experience and provide a reference basis for subsequent similar projects. The whole scheme uses artificial intelligence algorithm to process and analyze multi-source data, fully utilizes the advantages of deep learning in pattern recognition and feature extraction, realizes the intelligentization of the whole process from data collection, processing, analysis to decision support, and significantly improves the scientificity and reliability of the net frame and pipe truss construction safety monitoring.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, the system and the unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0121] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring a safety distance of a grid and pipe truss construction, characterized by, The safety distance monitoring method of the net rack and pipe truss construction comprises the following steps: The original data collected by the key node safety distance sensor, the construction state data collected by the working condition identification sensor and the environmental interference data collected by the environmental parameter sensor are integrated into a net rack safety distance monitoring original data set through a distributed data collection terminal; According to the net rack safety distance monitoring original data set, abnormal data is screened out and error compensation is performed to generate a standardized safety distance data stream; The standardized safety distance data stream is subjected to net rack deformation feature analysis, and a deformation correlation feature table is established according to node displacement data and working condition feature data to generate a net rack structure deformation state evaluation report, which comprises the following steps: a node safety distance monitoring network is established based on the standardized safety distance data stream and the topology structure of the net rack to output a spatial monitoring point group distribution matrix; a deformation gradient field is constructed along the main support direction of the net rack according to the spatial monitoring point group distribution matrix to form a net rack deformation measurement data set; the node deformation peak interval is counted with the aid of the net rack deformation measurement data set, and a working condition-deformation coupling data package is generated in combination with the working condition feature data; based on the working condition-deformation coupling data package, the key deformation node link of the net rack is extracted to construct a deformation propagation path map; the node deformation evolution law is analyzed through the deformation propagation path map to draw a deformation correlation feature table; the deformation correlation feature table and the overall stability index of the net rack are fused to output a net rack structure deformation state evaluation report; Based on the net rack structure deformation state evaluation report, a warning trigger condition is matched, and a dangerous area is located in combination with abnormal deformation mode recognition to output a net rack safety warning information package, which comprises the following steps: the deformation state of the net rack construction hoisting area, the welding reinforcement area and the component installation area is subdivided through the net rack structure deformation state evaluation report to generate a partition monitoring warning index; the node deformation feature caused by the movement of large construction equipment is analyzed by using the partition monitoring warning index to form equipment construction interference evaluation data; the equipment construction interference evaluation data is associated with the stability of the adjacent node support for analysis to establish a construction working condition influence coefficient list; the stress change law of the net rack node is extracted from the construction working condition influence coefficient list to mark a high stress concentration construction area; according to the deformation development trend of the high stress concentration construction area, a net rack construction dangerous operation area warning distribution map is drawn; the hierarchical warning threshold is set according to the net rack construction dangerous operation area warning distribution map to output the net rack safety warning information package; The key intervention node is determined according to the process influence evaluation matrix for the net rack safety warning information package to generate a net rack construction safety adjustment instruction; According to the net rack construction safety adjustment instruction and historical safety event data, a safety event feature correlation network is established to generate a net rack construction safety management knowledge base.

2. The method of claim 1, wherein the safety distance between the truss and the pipe truss is monitored. The original data collected by the key node safety distance sensor, the construction state data collected by the working condition identification sensor and the environmental interference data collected by the environmental parameter sensor are integrated into a net rack safety distance monitoring original data set through a distributed data collection terminal, which comprises the following steps: The node three-dimensional coordinate data collected by the key node safety distance sensor within a preset sampling period is converted into a safety distance original data set; The construction machinery position data, work personnel distribution data and material stacking state data collected by the working condition recognition sensor are integrated into a construction state feature data set; The temperature field data, humidity field data and vibration field data collected by the environmental parameter sensor are fused into an environmental interference feature data set; The safety distance original data set, the construction state feature data set and the environmental interference feature data set are time stamp matched to generate a time sequence correlation data table; The time sequence correlation data table is spatially mapped according to the node number to establish a net rack node safety distance monitoring spatial relationship matrix; According to the net rack node safety distance monitoring spatial relationship matrix and the time sequence correlation data table, the data is integrated in time and space dimensions to generate a net rack safety distance monitoring original data set. 3.The method of claim 1, wherein, According to the net rack safety distance monitoring original data set, abnormal data is screened out and error compensation is performed to generate a standardized safety distance data stream, including: The net rack safety distance monitoring original data set is divided into safety distance monitoring data sets according to the safety distance relationship between adjacent nodes; Based on the safety distance monitoring data set, a node safety distance change curve is constructed to generate a safety distance trend data table; According to the safety distance trend data table, a mutation point is detected, and a distance abnormal data point is marked to form a safety distance abnormal data record; The safety distance abnormal data record and the environmental interference data are associated to extract abnormal features caused by interference to generate an environmental interference influence evaluation table; According to the environmental interference influence evaluation table, the net rack safety distance monitoring original data set is filtered to obtain a net rack safety distance effective data set; The net rack safety distance effective data set is normalized according to a standardized processing procedure to generate a standardized safety distance data stream.

4. The safe distance monitoring method for the construction of the space truss and pipe truss according to claim 1, characterized in that, According to the net rack safety warning information package, the key intervention nodes are determined according to the process influence evaluation matrix to generate a net rack construction safety adjustment instruction, including: The net rack safety warning information package is split into node deformation data package, process interference data package and safety limit value data package to generate a classified warning factor table; According to the classified warning factor table, a force state analysis is performed on the net rack support points, connection nodes and main rod members to form a process influence evaluation matrix; High-risk construction process combinations are screened from the process influence evaluation matrix to compile a net rack construction intervention list; According to the net rack construction intervention list, a conflict check is performed on the hoisting process, welding process and reinforcement process to mark the node intervention priority; According to the node intervention priority, the section where the hazard source is located is divided into an emergency disposal area, a key control area and a conventional monitoring area to output a net rack key intervention node table; The net rack key intervention node table is converted into specific construction control measures to generate a net rack construction safety adjustment instruction.

5. The method of claim 1, wherein the safety distance between the truss and the pipe truss is monitored. According to the net rack construction safety adjustment instruction and historical safety event data, a safety event feature correlation network is established to generate a net rack construction safety management knowledge base, including: The construction process control focus, intervention measure requirement, and safety limit range are extracted from the net rack construction safety adjustment instruction to form a construction control experience data set; The net rack hoisting failure, node instability condition, and support deformation record in the historical safety event data are sorted to establish a construction risk case library; The construction control experience data set and the construction risk case library are scene-mapped to generate a net rack construction emergency disposal scheme set; With the aid of the net rack construction emergency disposal scheme set, the node instability type, deformation overrun reason, and environmental interference factor in different construction stages are classified, and an experience knowledge item table is sorted; Based on the experience knowledge item table, an association relationship among the construction accident prevention measures, emergency intervention means, and disposal effect evaluation is established to form a safety event feature association network; The management points, technical points, and operation points in the safety event feature association network are summarized to generate a net rack construction safety management knowledge base.

6. A safety distance monitoring method system for grid and pipe truss construction, for implementing the safety distance monitoring method for grid and pipe truss construction according to any one of claims 1-5, characterized in that, The safety distance monitoring method and system for the net rack and pipe truss construction include: A collection module is configured to integrate original data collected by a key node safety distance sensor, construction state data collected by a working condition identification sensor, and environmental interference data collected by an environmental parameter sensor into a net rack safety distance monitoring original data set through a distributed data collection terminal; A screening module is configured to screen out abnormal data and perform error compensation based on the net rack safety distance monitoring original data set to generate a standardized safety distance data stream; A generation module is configured to perform net rack deformation feature analysis on the standardized safety distance data stream, and establish a deformation correlation feature table based on node displacement data and working condition feature data to generate a net rack structure deformation state evaluation report, including: establishing a node safety distance monitoring network based on the net rack topological structure based on the standardized safety distance data stream to output a spatial monitoring point group distribution matrix; constructing a deformation gradient field along the main support direction of the net rack based on the spatial monitoring point group distribution matrix to form a net rack deformation measurement data set; statistically analyzing the node deformation peak interval based on the net rack deformation measurement data set, and generating a working condition-deformation coupling data package in combination with the working condition feature data; extracting a key deformation node link of the net rack based on the working condition-deformation coupling data package to construct a deformation propagation path atlas; analyzing the node deformation evolution law through the deformation propagation path atlas to draw a deformation correlation feature table; and fusing the deformation correlation feature table and the net rack overall stability index to output a net rack structure deformation state evaluation report. The positioning module is configured to match a pre-warning triggering condition based on the report of the deformation state of the grid structure, locate a dangerous area in combination with abnormal deformation mode recognition, and output a grid safety pre-warning information package, including: subdividing the deformation state of a grid construction hoisting area, a welding reinforcement area, and a component installation area via the report of the deformation state of the grid structure, generating partition monitoring pre-warning indexes; analyzing node deformation characteristics caused by movement of large construction equipment using the partition monitoring pre-warning indexes, forming equipment construction interference evaluation data; correlatively analyzing the equipment construction interference evaluation data and adjacent node support stability, establishing a list of construction condition influence coefficients; extracting grid node stress change rules from the list of construction condition influence coefficients, marking high stress concentration construction areas; drawing a grid construction dangerous operation area pre-warning distribution map according to the deformation development trend of the high stress concentration construction areas; setting graded pre-warning thresholds according to the grid construction dangerous operation area pre-warning distribution map, and outputting the grid safety pre-warning information package; The adjustment module is configured to determine key intervention nodes for the grid safety pre-warning information package according to a process influence evaluation matrix, and generate grid construction safety adjustment instructions; The management module is configured to establish a safety event feature correlation network and generate a grid construction safety management knowledge base according to the grid construction safety adjustment instructions and historical safety event data.

Images