A method for seismic damage identification and treatment of all-welded joints based on intelligent sensing

Abstract

This application provides a method for identifying and handling seismic damage to fully welded nodes based on intelligent sensing, relating to the field of intelligent monitoring and structural seismic damage identification technology. The method includes: establishing a monitoring object model of the fully welded intelligent node; collecting node operating status data; generating a damage monitoring identifier, a structural stability identifier, and a damage association identifier based on the humidity monitoring data and the acoustic emission monitoring data; determining the node status identifier corresponding to the current fully welded intelligent node based on the fusion result of the damage association identifier and the seismic damage status identifier; and sending the node status identifier and handling strategy to a monitoring terminal. This application solves the problems of easy loosening and damage risks in existing seismic-resistant pipeline connections, and the difficulty in timely detection of post-earthquake damage, achieving real-time monitoring and early warning of seismic damage and damage risk status, thereby improving the reliability and seismic safety of pipeline connections and significantly enhancing fault early warning capabilities.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring and structural seismic damage identification technology, and in particular to a method for identifying and treating seismic damage to all welded joints based on intelligent sensing. Background Technology

[0002] All-welded joints, as an important form of continuous connection between load-bearing components, are widely used in welded structures requiring long-term service. These joints are typically subjected to complex environments and alternating loads, especially under conditions such as seismic vibration and impact loads. Stress concentration and cumulative damage easily occur in the weld and its heat-affected zone, leading to crack initiation, crack propagation, and decreased structural stability. When joint damage develops to a certain extent, it may reduce the joint's load-bearing capacity, affecting the safety and reliability of the overall structure.

[0003] Existing methods for identifying node status primarily rely on manual inspections, periodic non-destructive testing, or online identification using single sensors. Manual inspections and periodic testing suffer from long cycles, insufficient real-time performance, and difficulty in capturing damage evolution characteristics after transient events such as earthquakes. While single-sensor identification can acquire certain types of status information, it is susceptible to environmental interference and threshold drift under complex operating conditions, making it difficult to simultaneously reflect multi-dimensional states such as crack activity, structural impact response, and abnormal environmental humidity. This leads to false alarms, missed alarms, and inaccurate assessments of damage mechanisms. Furthermore, after strong vibration events such as earthquakes, node status often exhibits characteristics with temporal and spatial correlations, such as "changes in vibration and impact response—increased crack activity—abnormal environmental humidity." Although existing technologies can acquire multi-source monitoring information such as cracks, vibration, and environmental conditions, they typically employ independent judgments or simple threshold fusion methods for various monitoring results, lacking a unified node status adjudication mechanism. This makes it difficult to convert damage information from different sources into a unified node status result, resulting in insufficient consistency in node risk assessment results and hindering direct support for engineering operation and maintenance and status management. Meanwhile, existing solutions typically lack a unified mapping mechanism from damage identification results to node status results, making it impossible to comprehensively assess damage risk and seismic damage risk and generate a unified node status identifier. It is also difficult to directly associate the corresponding handling strategies based on the node status, resulting in identification results that are difficult to directly support rapid on-site decision-making and operation and maintenance.

[0004] Therefore, there is an urgent need for a method for identifying and addressing seismic damage in fully welded joints under conditions such as earthquake vibration and impact loads. This method would collect information from multiple sources, including humidity monitoring, acoustic emission monitoring, and vibration monitoring, and combine this with damage correlation analysis, seismic damage status identification, and joint status fusion adjudication. This would allow for a unified risk assessment of damage information from different sources, generating corresponding joint status identifiers and treatment strategies. This would enable accurate identification of joint damage risks, unified status determination, and output of treatment strategies, thereby improving the accuracy of seismic damage identification, the consistency of status determination, and the efficiency of operation and maintenance for fully welded joints. Summary of the Invention

[0005] The purpose of this application is to provide a method for seismic damage identification and treatment of all-welded joints based on intelligent sensing, in order to solve the problems of existing technologies that rely heavily on manual inspections, periodic testing, and single sensor threshold judgments. Existing technologies lack the fusion analysis of multi-source information such as humidity monitoring, acoustic emission monitoring, and vibration monitoring, making it difficult to timely and accurately identify and classify crack propagation and structural stability changes in joints under conditions such as seismic vibration and impact loads. This results in high false alarm and false negative rates, insufficient reliability of joint status output, and thus affects the seismic safety monitoring capabilities and maintenance efficiency of all-welded joints.

[0006] In view of the above problems, this application provides a method for identifying and treating seismic damage to all welded joints based on intelligent perception.

[0007] In a first aspect, this application provides a method for identifying and addressing seismic damage to fully welded nodes based on intelligent sensing. The method includes: acquiring node identification information and structural parameter information of the fully welded intelligent node to be monitored; determining sensor installation parameters and monitoring zone parameters based on the structural parameter information; and establishing a monitoring object model of the fully welded intelligent node. The structural parameter information includes the weld node's external dimensions, wall thickness, and weld location parameters. A humidity sensor, an acoustic emission sensor, and an acceleration sensor are installed at the fully welded intelligent node to collect node operating status data. The node operating status data includes humidity monitoring data, acoustic emission monitoring data, and vibration monitoring data. A damage monitoring identifier is generated based on the humidity monitoring data and the acoustic emission monitoring data. The damage monitoring identifier includes at least the humidity... The system includes a humidity anomaly identifier and a crack propagation identifier. Specifically, the humidity anomaly identifier is generated based on the humidity monitoring data, and the crack propagation identifier is generated based on the acoustic emission monitoring data. Vibration and impact characteristic parameters are extracted from the vibration monitoring data. Based on these parameters, the structural stability of the fully welded intelligent node is analyzed to generate a structural stability identifier. A correlation analysis is performed between the structural stability identifier, the humidity anomaly identifier, and the crack propagation identifier to generate a damage correlation identifier. The corresponding vibration damage status identifier is determined based on the vibration monitoring data. Based on the fusion result of the damage correlation identifier and the vibration damage status identifier, the node status identifier corresponding to the current fully welded intelligent node is determined. A corresponding treatment strategy is determined based on the node status identifier. The node status identifier and the treatment strategy are then sent to the monitoring terminal.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application provides a method for seismic damage identification and treatment of all-welded nodes based on intelligent sensing. By establishing a monitoring object model of the all-welded intelligent node and combining it with node structural parameter information, the method determines sensor installation parameters and monitoring zone parameters, providing a unified spatial reference and scale benchmark for the monitored object and monitoring data, thus improving the comparability and traceability of multi-source data fusion. By deploying humidity sensors, acoustic emission sensors, and acceleration sensors at the all-welded intelligent node, a multi-source state observation channel for humidity, crack activity, and vibration impact response is formed. Compared to single-sensor threshold judgment, this method can simultaneously cover key failure link information such as abnormal environmental humidity, crack propagation signs, and changes in structural stability, significantly reducing the risk of missed detections. Furthermore, by generating humidity anomaly markers based on humidity monitoring data and extracting crack activity characteristics from acoustic emission monitoring data to generate crack propagation markers, early identification of crack initiation and propagation processes is achieved. By extracting vibration impact characteristic parameters from vibration monitoring data and calculating structural impact response parameters, structural stability markers are generated, enabling the quantitative characterization of the node's response intensity and attenuation characteristics under seismic vibration, impact load, and other conditions, thereby improving the ability to discriminate structural stability deterioration. Building upon this foundation, this application introduces a correlation analysis mechanism based on temporal consistency and spatial coupling. It utilizes time offset and spatial coupling parameters to construct damage correlation judgment quantities and parameters, enabling quantitative discrimination of the correlation between multiple sources of events—"structural stability change—humidity anomaly—crack propagation." This overcomes the problems of traditional empirical rules being ill-suited to complex working conditions and prone to false alarms and misjudgments. Simultaneously, this application segments, extracts features from, and grades vibration events, combining vibration intensity, duration, frequency domain judgment, and hysteresis suppression rules to generate seismic damage status identifiers. This effectively reduces false triggering caused by transient impacts and improves the stability and robustness of post-earthquake status assessment. Furthermore, this application inputs the damage correlation identifier and seismic damage status identifier into a logical adjudication module, constructs state combination parameters, and introduces a node state calculation model to output node state identifiers. This achieves hierarchical output of monitoring results from "multi-source perception—risk assessment—state adjudication," facilitating rapid on-site understanding and decision-making. Finally, this application can automatically generate disposal strategies based on node status identifiers and send them to the monitoring terminal, realizing integrated linkage of alarm prompts, operation and maintenance suggestions and information release, improving the efficiency of post-earthquake inspection and disposal, reducing reliance on manual labor, and enhancing the long-term safe operation guarantee capability of all-welded nodes in seismic scenarios.

[0009] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating a method for identifying and treating seismic damage to all-welded joints based on intelligent sensing, as proposed in this application. Detailed Implementation

[0012] This application provides a method for identifying and handling seismic damage to all-welded nodes based on intelligent sensing. It solves the problems in the prior art, such as the difficulty in unifying and integrating multi-source monitoring information, the lack of collaborative evaluation of damage risk and seismic damage risk, and the lack of a unified adjudication mechanism for node status. By constructing a correlation calculation mechanism between damage risk evaluation parameters, seismic damage risk evaluation parameters, and node status parameters, it realizes the mapping from multi-source monitoring results to unified node status results and generates corresponding handling strategies based on node status. This improves the accuracy of node damage identification, the consistency of node status determination, and the reliability of operation and maintenance, and significantly enhances the safety monitoring and risk warning capabilities of all-welded nodes under seismic vibration and impact load conditions.

[0013] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0014] Example 1 Please see the appendix Figure 1This application provides a method for identifying and treating seismic damage to fully welded joints based on intelligent sensing. The method specifically includes the following steps: S1: Obtain the node identification information and structural parameter information of the fully welded intelligent node to be monitored, and determine the sensor installation parameters and monitoring zone parameters based on the structural parameter information to establish the monitoring object model of the fully welded intelligent node; wherein, the structural parameter information includes the welding node's external dimension parameters, wall thickness parameters, and weld position parameters.

[0015] Specifically, in this embodiment, step S1 is used to establish the monitoring object and calibrate the parameters of the fully welded intelligent node, so that subsequent multi-source monitoring data can be aligned, correlated, and fused under a unified spatial reference and structural scale. Specifically, firstly, the node identification information of the fully welded intelligent node to be monitored is obtained. This node identification information is used to uniquely identify and manage different monitoring objects, and to realize node file establishment, data archiving, and historical tracing on the monitoring terminal side. The node identification information may include at least one of node number, installation location code, equipment number, and monitoring object type identifier. Further, the structural parameter information of the fully welded intelligent node is obtained. This structural parameter information is used to characterize the geometric dimensions and weld distribution characteristics of the welded node, and provides basic data support for sensor installation location selection, monitoring zone division, and spatial coupling calculations in correlation analysis. In some embodiments, the structural parameter information includes the welded node's external dimensions, wall thickness, and weld location parameters. The dimensional parameters of the welded node may include the node's outer diameter, node length, weld transition section dimensions, weld circumferential length, and weld coverage angle. The wall thickness parameters reflect the differences in load-bearing capacity and seismic response of key parts of the node and may include the node's main wall thickness, welded area wall thickness, and locations of wall thickness variations. The weld location parameters describe the spatial distribution characteristics of the weld on or inside the node surface and may include the circumferential weld location, longitudinal weld location, weld start and end locations, and the relative distance between the weld and the structural reference point. After obtaining the above structural parameter information, sensor installation parameters and monitoring zone parameters are determined based on the structural parameter information. The sensor installation parameters constrain the sensor's installation position, installation direction, number of sensors, and installation reference on the node, ensuring that the humidity sensor, acoustic emission sensor, and accelerometer can cover the weld and its surrounding key areas, and improving the spatial consistency of data collected by different sensors. In some embodiments, the sensor installation parameters include at least one of the following: sensor installation zone number, sensor distance relative to the weld, sensor installation angle, sensor installation orientation, and sensor installation height. The monitoring partitioning parameters are used to divide the welded node into regions, dividing the node surface or key areas into multiple monitoring partitions, and establishing a mapping relationship between sensor installation locations and monitoring partitions. Through the monitoring partitioning parameters, the location of events can be expressed in partitions during subsequent correlation analysis, thereby enabling the calculation of spatial coupling parameters, anomaly localization, and partitioned output of handling strategies. In some embodiments, the monitoring partitioning parameters include the number of partitions, partition boundary parameters, partition numbering rules, and partition adjacency parameters. Based on the node identification information, structural parameter information, sensor installation parameters, and monitoring partitioning parameters, a monitoring object model of the fully welded intelligent node is established.It should be noted that the monitoring object model in this embodiment is not a machine learning model, prediction model, or mathematical calculation model, but rather a structured data organization form used to describe the structural characteristics of the fully welded intelligent node, the sensor deployment relationship, and the monitoring area mapping relationship. The monitoring object model is used to associate and store node identification information, structural parameter information, sensor installation parameters, and monitoring zone parameters according to a preset data format, thereby forming a digital structural archive of the corresponding monitoring object. In some embodiments, the monitoring object model includes a node identification unit, a structural parameter unit, a sensor configuration unit, and a monitoring zone unit; wherein, the node identification unit is used to record the unique identification information of the monitoring object, the structural parameter unit is used to record the node geometric structure parameters and weld distribution parameters, the sensor configuration unit is used to record the installation position and installation parameters of the humidity sensor, acoustic emission sensor, and accelerometer, and the monitoring zone unit is used to record the boundary information and zone mapping relationship of each monitoring zone. After establishing the monitoring object model, the subsequently collected humidity monitoring data, acoustic emission monitoring data, and vibration monitoring data can be mapped to the corresponding monitoring zones and corresponding structural locations. This allows different types of monitoring data to be correlated and analyzed under a unified node coordinate system and a unified monitoring zone system, thereby providing basic data support for subsequent crack propagation identification, medium seepage identification, spatial coupling analysis, and seismic node status determination.

[0016] S2: A humidity sensor, an acoustic emission sensor, and an acceleration sensor are installed at the fully welded intelligent node to collect node operating status data; wherein, the node operating status data includes humidity monitoring data, acoustic emission monitoring data, and vibration monitoring data.

[0017] Specifically, in this embodiment, S2 is used to construct a multi-source state sensing channel for the fully welded intelligent node. Through humidity, acoustic emission, and vibration monitoring, it enables comprehensive observation of node environmental anomalies, crack activity, and seismic shock response, providing a data foundation for subsequent damage identification, correlation analysis, and node state determination. Specifically, a humidity sensor, an acoustic emission sensor, and an accelerometer are installed at the fully welded intelligent node, and each sensor is installed, fixed, and configured with parameters to continuously collect node operating status data during node operation. The humidity sensor is used to acquire humidity monitoring data of the node surface and its surrounding area to reflect changes in node protection status, environmental humidity intrusion, and abnormal humidity on the node surface. Humidity monitoring data may include relative humidity values, humidity changes, humidity change rates, and the time of occurrence of humidity anomalies. In some embodiments, the humidity sensor may be located in areas around the weld that are susceptible to environmental influences or in areas with weak node protection, and the humidity data may be correlated with the corresponding zones based on the monitoring zone parameters determined in S1. The acoustic emission sensor is used to acquire transient elastic wave signals generated during the initiation and propagation of cracks within the node material, thereby forming acoustic emission monitoring data. Acoustic emission monitoring data can include characteristic information such as acoustic emission event count, event amplitude, energy, peak frequency, cumulative energy, and arrival time. By acquiring and extracting features from acoustic emission signals, early identification can be achieved before crack propagation reaches visible damage, improving the sensitivity of node damage monitoring. In some embodiments, acoustic emission sensors can be deployed in key areas near welds, and combined with monitoring zoning parameters to achieve zonal localization of crack activity events. The accelerometer is used to acquire vibration monitoring data of nodes under external excitations such as seismic vibration and impact loads to characterize the dynamic response characteristics of the nodes. Vibration monitoring data can include acceleration time history data, peak acceleration, root mean square acceleration, impact duration, dominant frequency component, impact energy, and other information. By segmenting, denoising, and extracting features from the vibration monitoring data, it can be further used for calculating structural impact response parameters and determining seismic damage status, thereby reflecting changes in node structural stability and post-earthquake status. During multi-source data acquisition, the humidity sensor, acoustic emission sensor, and accelerometer can be unified in time reference and timestamped to form node operating status data with a unified time scale. The node operating status data includes humidity monitoring data, acoustic emission monitoring data, and vibration monitoring data, and can be further bound and stored with node identification information and monitoring partition parameters for subsequent event matching, temporal consistency analysis, spatial coupling analysis, and node status assessment, thereby realizing the seismic and seismic damage identification of the fully welded intelligent node.

[0018] S3: Generate a damage monitoring identifier based on the humidity monitoring data and the acoustic emission monitoring data. The damage monitoring identifier includes at least a humidity anomaly identifier and a crack propagation identifier. The humidity anomaly identifier is generated based on the humidity monitoring data, and the crack propagation identifier is generated based on the acoustic emission monitoring data.

[0019] Furthermore, step S3 of this application also includes: S31. Acquire humidity monitoring data collected by a humidity sensor, and filter the humidity monitoring data to extract humidity change amount and humidity change rate parameters; S32. Compare the humidity change amount and humidity change rate parameters with a preset humidity threshold to generate humidity anomaly judgment parameters, and generate a humidity anomaly identifier based on the humidity anomaly judgment parameters; S33. Acquire acoustic emission monitoring data collected by an acoustic emission sensor, and extract features from the acoustic emission monitoring data to obtain crack activity feature parameters, wherein the crack activity feature parameters include at least one or more of event count, amplitude, energy, peak frequency or cumulative energy, and generate a crack activity identifier; S34. Match the crack activity identifier with a preset crack propagation judgment condition to generate crack propagation judgment parameters, and generate a crack propagation identifier based on the crack propagation judgment parameters.

[0020] Specifically, in this embodiment, step S3 is used to identify and generate labels from multi-source monitoring data to form a priori judgment result for the damage evolution of welded nodes, providing input for subsequent structural stability correlation analysis and node status adjudication. Specifically, damage monitoring labels are generated based on humidity monitoring data and acoustic emission monitoring data. These labels include at least a humidity anomaly label and a crack propagation label. The humidity anomaly label characterizes an abnormal change in humidity on or around the welded node surface, while the crack propagation label characterizes an increased crack activity and propagation trend within the welded node. Further, step S3 includes the following sub-steps: In S31, humidity monitoring data collected by a humidity sensor is acquired. To reduce the impact of environmental noise, transient disturbances, and acquisition errors on the judgment result, the humidity monitoring data can be filtered, for example, using moving average filtering, median filtering, or low-pass filtering. Then, humidity change and humidity change rate parameters are extracted from the filtered humidity monitoring data. The humidity change can be the difference in humidity values ​​between adjacent sampling times, and the humidity change rate parameter can be the ratio of humidity changes per unit time, used to characterize the magnitude and trend of humidity changes. In S32, the humidity change amount and humidity change rate parameters are compared with a preset humidity threshold to generate humidity anomaly judgment parameters, and a humidity anomaly identifier is generated based on these parameters. The preset humidity threshold can be set according to the node operating environment, sensor range, historical statistical values, or engineering experience. In some embodiments, both the humidity change amount threshold and the humidity change rate threshold can be set simultaneously, and humidity anomalies can be judged in conjunction with duration conditions, thereby suppressing misjudgments caused by non-structural factors such as short-term water mist and condensation. The humidity anomaly identifier can be used to indicate whether a humidity anomaly event has occurred, and can further record information such as the time of occurrence of the anomaly, the duration of the anomaly, and the monitoring zone corresponding to the anomaly. In S33, acoustic emission monitoring data collected by the acoustic emission sensor is acquired, and feature extraction is performed on the acoustic emission monitoring data to obtain crack activity characteristic parameters and generate a crack activity identifier. Acoustic emission monitoring data usually manifests as a series of transient event signals, which can be used for event detection and feature calculation. Crack activity characteristic parameters include at least one or more of event count, amplitude, energy, peak frequency, and cumulative energy, used to characterize the frequency, intensity level, and energy accumulation trend of crack activity. In some implementations, crack activity identifiers are used to describe whether crack activity is active, and can record the time and location information of crack activity events for subsequent correlation analysis with structural stability events. In S34, the crack activity identifier is matched with preset crack propagation judgment conditions to generate crack propagation judgment parameters, and crack propagation identifiers are generated accordingly. The preset crack propagation judgment conditions can be set based on threshold combinations of crack activity characteristic parameters, cumulative energy growth trends, event count growth trends, or the changing patterns of characteristic parameters within a statistical window.Through the above matching process, "enhanced crack activity" can be further determined as "cracks are trending towards expansion," thus outputting a crack expansion indicator. This crack expansion indicator can serve as an important input for subsequent damage correlation determination, used in conjunction with structural stability and humidity anomaly indicators to construct a damage correlation determination metric, thereby improving the accuracy and reliability of nodal damage identification.

[0021] S4: Extract vibration and impact characteristic parameters based on the vibration monitoring data, analyze the structural stability of the fully welded smart node based on the vibration and impact characteristic parameters, generate a structural stability identifier, and perform correlation analysis based on the structural stability identifier, the humidity anomaly identifier, and the crack propagation identifier to generate a damage correlation identifier.

[0022] Furthermore, step S4 of this application also includes: S41. Acquire vibration monitoring data collected by an accelerometer, and perform noise reduction and segmentation processing on the vibration monitoring data to extract vibration impact characteristic parameters; wherein, the vibration impact characteristic parameters include at least one or more of peak acceleration, root mean square acceleration, impact duration, dominant frequency component, or impact energy; S42. Calculate structural impact response parameters based on the vibration impact characteristic parameters, wherein the structural impact response parameters are used to characterize the response intensity and response attenuation characteristics of the all-welded smart node under vibration impact; S43. Compare the structural impact response parameters with a preset structural stability threshold to generate structural stability judgment parameters, and generate a structural stability identifier based on the structural stability judgment parameters; S44. When both the temporal consistency parameter and the spatial coupling parameter exceed the preset threshold, construct a damage correlation judgment quantity R, and generate a damage correlation identifier.

[0023] Furthermore, step S44 of this application also includes: S44-1. Obtain the structural stability indicator, humidity anomaly indicator, and crack propagation indicator, and extract the corresponding occurrence time sequence and partition location information respectively; S44-2. Calculate the time offset between the structural stability indicator and the humidity anomaly indicator based on the occurrence time sequence. And according to the time offset Generate timing consistency parameters; S44-3, Calculate the spatial coupling parameters between crack propagation markers and structural stability markers based on the partition location information. S44-4. Construct a damage association determination quantity R based on the temporal consistency parameter and the spatial coupling parameter, generate damage association determination parameters based on the damage association determination quantity R, and generate a damage association identifier based on the damage association determination parameters.

[0024] Furthermore, step S44-1 of this application also includes: S44-1-1. Perform time base unification and timestamp correction on the event data corresponding to the structural stability indicator, humidity anomaly indicator, and crack propagation indicator to generate an event sequence under a unified time scale; S44-1-2. Extract the time sequence of structural stability events, humidity anomaly events, and crack propagation events respectively; S44-1-3. Divide the welded nodes into regions according to the structural size parameters of the welded nodes and the preset partitioning rules to generate monitoring partition parameters; map the humidity anomaly events and crack propagation events to the corresponding partitions to generate partition location information; S44-1-4. Calculate the event confidence parameters of the humidity anomaly indicator and crack propagation indicator respectively, and generate confidence correction parameters.

[0025] Furthermore, step S44-2 of this application also includes: S44-2-1. Determine the correlation analysis time window parameters, wherein the time window parameters are determined based on the structural impact response parameters; S44-2-2. Under the constraints of the time window parameters, perform event matching on the time series of structural stability events and the time series of humidity anomaly events to obtain a set of matched event pairs; S44-2-3. Calculate the time offset based on the set of matched event pairs. and the time offset Normalization is performed to obtain the timing consistency parameters.

[0026] Specifically, step S4 is used to quantitatively analyze the structural stability of the fully welded intelligent node based on vibration monitoring data, and further correlate the structural stability indicator with the humidity anomaly indicator and crack propagation indicator to form a damage correlation judgment result, thereby improving the accuracy of identifying node damage evolution and anti-interference capability. Since the node state often exhibits a coupling relationship between changes in structural dynamic response and enhanced crack activity under conditions such as seismic vibration and impact loads, a single information source is easily affected by noise and random events. Therefore, structural stability analysis and multi-source correlation judgment can effectively suppress misjudgments and improve monitoring reliability. Further, step S4 includes the following sub-steps. In S41, vibration monitoring data collected by an accelerometer is acquired, and the vibration monitoring data is denoised and segmented. Denoising can be used to reduce the influence of environmental noise, equipment interference, and high-frequency stray components on feature extraction; segmentation is used to identify vibration event data segments from continuous vibration signals, for example, by determining the start and end times of vibration events through trigger thresholds, energy thresholds, or window statistics. Subsequently, vibration impact characteristic parameters are extracted, which characterize the amplitude, energy, and duration of vibration impact. In some embodiments, the vibration and impact characteristic parameters include at least one or more of peak acceleration, root mean square acceleration, impact duration, dominant frequency component, and impact energy. In S42, structural impact response parameters are calculated based on the vibration and impact characteristic parameters. These parameters characterize the response intensity and response attenuation characteristics of the fully welded intelligent node under vibration and impact, reflecting the dynamic stiffness changes, damping changes, and response anomalies caused by local damage under impact loads. The structural impact response parameters can be calculated by combining characteristic parameters such as peak acceleration, root mean square acceleration, and impact energy, and the response can be normalized by incorporating the event duration to enhance comparability between different events. In S43, the structural impact response parameters are compared with a preset structural stability threshold to generate structural stability judgment parameters, and a structural stability identifier is generated accordingly. The preset structural stability threshold can be set based on historical baseline data of the node, engineering experience values, or reference thresholds for different node types. This comparison process converts the changing trend of structural impact response into structural stability indicators, which characterize whether the nodal structural stability is in a normal, warning, or abnormal state. It can also carry additional information such as event occurrence time and event level for subsequent analysis. In S44, structural stability indicators, humidity anomaly indicators, and crack propagation indicators are acquired, and correlation analysis is performed based on their temporal consistency and spatial coupling relationship.Temporal consistency is used to characterize the temporal correspondence of different monitoring events, such as the occurrence of humidity anomaly and crack propagation events within a preset time window after a structural stability anomaly. Spatial coupling is used to characterize the correlation of different events in monitoring zones or locations, such as the adjacency and distance relationships between humidity anomaly zones, crack propagation zones, and structurally sensitive zones. Based on the above temporal consistency and spatial coupling relationships, a damage correlation judgment quantity R is constructed, and damage correlation judgment parameters are generated based on the damage correlation judgment quantity R, thereby generating a damage correlation identifier. The damage correlation identifier is used to characterize the degree of multi-source consistency of node damage events and can serve as an important input for subsequent node status adjudication, thereby achieving a more reliable judgment and graded assessment of node damage risk. Through the above steps, this implementation method can correlate and fuse structural response changes caused by vibration and shock with multi-source information such as humidity anomalies and crack propagation. It can not only use vibration response to quickly capture post-earthquake structural stability changes, but also use acoustic emission signals to sensitively identify crack propagation trends, and combine humidity anomaly information to provide auxiliary evidence, thereby improving the accuracy, stability, and engineering applicability of seismic damage identification of all-welded intelligent nodes.

[0027] Furthermore, step S44 establishes a correlation determination mechanism among structural stability markers, humidity anomaly markers, and crack propagation markers to improve the reliability of damage identification by leveraging the consistency characteristics of multi-source events in spatial location and temporal sequence. S44-1 is used to organize and align the spatiotemporal information of the multi-source marker events. Specifically, structural stability markers, humidity anomaly markers, and crack propagation markers are obtained, and the occurrence time sequence and partition location information corresponding to each marker are extracted. The occurrence time sequence represents the occurrence time of each type of event, and the partition location information represents the location of the event within the monitoring partition, providing basic input for subsequent temporal consistency analysis and spatial coupling analysis. S44-2 represents the correspondence between structural stability events and humidity anomaly events in the time dimension. Specifically, the time offset between the structural stability marker and the humidity anomaly marker is calculated based on the occurrence time sequence obtained in S44-1. And according to the time offset Generate temporal consistency parameters. These parameters reflect the degree of synchronization or sequential relationship between two types of events within a preset time window and serve as an important input for subsequent damage correlation determination. In S44-3, spatial coupling parameters between crack propagation indicators and structural stability indicators are calculated based on partition location information. Specifically, based on the monitoring partition parameters established in step S1, the monitoring area of ​​the welding node is divided into multiple monitoring partitions, and each partition is assigned a partition number and partition boundary information. For crack activity events corresponding to crack propagation identifiers, the corresponding crack propagation event partition number can be obtained; for structural stability events corresponding to structural stability identifiers, the corresponding structural stability event partition number can be obtained. In some embodiments, to characterize the spatial proximity relationship between partitions, partition adjacency relationship parameters can be constructed. For example, a partition adjacency matrix A can be established, where the corresponding element is 1 when two partitions are adjacent and 0 when two partitions are not adjacent; or a partition distance matrix D can be constructed to represent the shortest path distance or geometric center distance between any two partitions. Based on the adjacency relationship parameters or distance matrix, the spatial relationship between crack propagation event partitions and structural stability event partitions can be mapped to spatial coupling parameters. For example, when the crack propagation event partition is the same as or adjacent to the structural stability event partition, set... A higher coupling value is set; as the distance between the two partitions increases, the value is adjusted accordingly. The value decreases with increasing distance to reflect the weakening spatial consistency of the damage event. In some implementations, Furthermore, weighted corrections can be made by incorporating weld location parameters, resulting in higher contributions from zoned coupling near the weld-sensitive area, thus better aligning with the spatial distribution characteristics of weld joint damage evolution. Through these methods, spatial coupling parameters... This can be used to characterize the spatial consistency between crack propagation events and structural stability anomalies, providing input for the subsequent construction of damage correlation determination parameters. In S44-4, a damage correlation determination parameter R is constructed based on temporal consistency parameters and spatial coupling parameters, and further damage correlation determination parameters and damage correlation identifiers are generated. Specifically, firstly, the temporal consistency parameter obtained in S44-2 is obtained, which is used to characterize the correspondence between structural stability events and humidity anomalies within a preset time window. Subsequently, the spatial coupling parameter obtained in S44-3 is obtained. This parameter characterizes the spatial consistency between crack propagation events and structural stability events within the monitoring zone. A damage correlation determination quantity R is constructed based on these two types of parameters, where R comprehensively characterizes the degree of joint satisfaction of "temporal consistency" and "spatial consistency." In some embodiments, the temporal consistency parameter and spatial coupling parameter can be normalized to ensure their values ​​are within a unified range for fusion calculation. After constructing the damage correlation determination quantity R, damage correlation determination parameters are generated based on R. For example, a correlation determination result is obtained by comparing R with a preset correlation threshold range, and this result is output as the damage correlation determination parameter. Further, a damage correlation identifier is generated based on the damage correlation determination parameter. This identifier indicates whether the current multi-source monitoring events have consistent damage orientation and whether the degree of damage correlation is at a normal, warning, or abnormal level. In some embodiments, the damage correlation identifier can be recorded along with the event occurrence time, corresponding monitoring zone, determination quantity R value, and determination level for subsequent node status adjudication, handling strategy generation, and monitoring terminal display.

[0028] Furthermore, in this embodiment, the event information corresponding to structural stability indicators, humidity anomaly indicators, and crack propagation indicators is preprocessed and standardized to ensure a consistent alignment basis for multi-source events in both time and space dimensions, providing reliable input for subsequent calculations of temporal consistency parameters and spatial coupling parameters. In S44-1-1, the event data corresponding to structural stability indicators, humidity anomaly indicators, and crack propagation indicators are unified in terms of time reference and timestamp correction to generate event sequences under a unified time scale. By unifying the time reference, the time inconsistency caused by clock deviations from different sensors, differences in sampling periods, and data transmission delays can be eliminated, thereby ensuring the accuracy of subsequent event matching and offset calculations. In S44-1-2, the time sequences of structural stability events, humidity anomaly events, and crack propagation events are extracted respectively. These event time sequences are used to characterize the occurrence time points and temporal distribution characteristics of various events, and can be further recorded along with event level, event duration, and other information to support subsequent time window matching and temporal consistency analysis. In step S44-1-3, the welding nodes are divided into regions according to the structural size parameters of the welding nodes and preset zoning rules, generating monitoring zoning parameters; and humidity anomaly events and crack propagation events are mapped to corresponding zoning regions, generating zoning location information. The structural size parameters of the welding nodes are obtained by reading at least one of the following methods: reading design and manufacturing data, on-site measurement, and three-dimensional measurement, and stored in the structural parameter file corresponding to the node identification information. The monitoring zoning parameters may include the number of zoning regions, zoning boundaries, zoning numbers, etc. Through zoning mapping, the location expression of multi-source events can be converted from continuous coordinates to zoning number expression, which facilitates the subsequent spatial coupling relationship calculation, anomaly location, and zoning output of handling strategies. In step S44-1-4, the event confidence parameters of the events corresponding to the humidity anomaly identifier and crack propagation identifier are calculated respectively, and confidence correction parameters are generated based on the event confidence parameters for subsequent weighted adjustment of damage correlation judgment quantities. Taking the humidity anomaly event as an example, let the humidity anomaly feature quantity be... The preset humidity threshold is The threshold deviation parameter is defined as follows: Let the duration of the event be... The preset minimum duration threshold is The persistence parameter is then defined as: Let the event signal-to-noise ratio be... The preset signal-to-noise ratio threshold is The signal-to-noise ratio parameter is defined as: Suppose that the stability of the characteristic parameters is characterized by the coefficient of variation, where the coefficient of variation is... The preset stability threshold is The stability parameter is then defined as: ;in, A minimum positive number is preset to avoid a denominator of zero. A confidence level for humidity anomaly events is constructed based on these parameters. The definition is as follows: ;in, For preset weighting coefficients, This is a limiting function used to... Limited to the range Inside. The weighting coefficients , , and The pre-set reliability fusion weights are obtained through at least one of the following methods: expert experience setting, experimental calibration, or historical data statistical learning; the weight coefficients satisfy the normalization constraint condition: ; This ensures that the comprehensive event confidence parameter accurately reflects the contribution of each confidence feature to the event's authenticity. Taking a crack propagation event as an example, let the acoustic emission crack activity feature quantity be... The preset judgment threshold is The event lasted for The signal-to-noise ratio is The stability coefficient of variation is Then, the sub-parameters of the crack propagation event can be calculated in the same way as those of the humidity anomaly event, and the confidence level of the crack propagation event can be obtained. Similarly, the following conditions are met: Furthermore, confidence correction parameters are generated based on the event confidence parameters, which are used for weighted adjustments of subsequent damage correlation determination quantities. Let the humidity anomaly confidence correction coefficient be... The crack propagation confidence correction factor is The basic form is defined as follows: Further, confidence correction parameters are generated based on the event confidence parameters, which are used for weighted adjustment of subsequent damage correlation determination quantities. Let the humidity anomaly confidence correction coefficient be... The crack propagation confidence correction factor is The basic form is defined as: In some implementations, to enhance the suppression effect of low-confidence events, a power-law enhancement method is used: ;in, , This is a preset enhancement coefficient. When the enhancement coefficient is greater than 1, it can enhance the attenuation effect on low-confidence events, thereby reducing the impact of low-confidence events on the damage association results in the subsequent association determination process and improving the robustness and stability of the system.

[0029] Further, in S44-2-1, the correlation analysis time window parameter is determined. This time window parameter limits the time range for event matching to avoid mismatching unrelated, distant events. The time window parameter is determined based on the structural impact response parameter. For example, a larger structural impact response parameter indicates a stronger impact, and the time window can be appropriately increased to cover the lag process of post-impact state changes; conversely, a smaller time window can be used when the structural impact response parameter is small to improve matching accuracy. In S44-2-2, under the constraint of the time window parameter, event matching is performed on the time sequence of structural stability events and the time sequence of humidity anomaly events to obtain a set of matched event pairs. Specifically, using the occurrence time of structural stability events as a benchmark, the occurrence time of humidity anomaly events is searched within the time window range, and events satisfying the time window constraint are grouped into a set of matched event pairs, representing candidate matching results where the two types of events have a temporal correspondence. In S44-2-3, the time offset is calculated based on the set of matched event pairs, and the time offset is normalized to obtain a temporal consistency parameter. The time offset is used to characterize the time difference between structural stability events and humidity anomaly events; normalization is used to eliminate the influence of different time window scales on the comparability of the offset, so that the obtained temporal consistency parameters can characterize the degree of event time matching within a unified range, thereby facilitating their participation in subsequent damage association determination together with spatial coupling parameters.

[0030] S5: Determine the corresponding vibration damage status indicator based on the vibration monitoring data.

[0031] Furthermore, step S5 of this application also includes: S51. Acquire vibration monitoring data collected by an accelerometer, and perform noise reduction, coordinate axis synthesis, and segmentation on the vibration monitoring data to obtain vibration event data segments; S52. Extract features from the vibration event data segments to obtain a set of vibration impact feature parameters, which includes at least one or more of peak acceleration, root mean square acceleration, impact duration, dominant frequency component, and impact energy; S53. Calculate vibration damage risk assessment parameters based on the set of vibration impact feature parameters, and compare the vibration damage risk assessment parameters with a preset vibration damage threshold range to generate vibration damage state determination parameters; S54. Generate vibration damage state identifiers based on the vibration damage state determination parameters, which include at least one of normal, minor vibration damage, moderate vibration damage, and severe vibration damage; S55. Apply hysteresis judgment rules to the vibration damage state identifiers to maintain the state and suppress switching, so as to reduce misjudgments caused by transient vibration impacts.

[0032] Furthermore, step S53 of this application also includes: S53-1. Obtain the vibration impact characteristic parameters, and perform baseline correction, denoising, and windowing processing on the vibration event data segments corresponding to the vibration impact characteristic parameters to extract vibration amplitude data and vibration duration data; wherein, the vibration amplitude data includes peak acceleration data and root mean square acceleration data; the vibration duration data includes vibration event duration data and duration data exceeding a preset trigger threshold; S53-2. Calculate vibration intensity parameters based on the vibration amplitude data, the vibration intensity parameters including peak intensity parameters and root mean square intensity parameters, and compare the vibration intensity parameters with a preset vibration intensity threshold range to generate vibration intensity judgment parameters; S53-3. Calculate the vibration duration parameters based on the vibration duration data, and perform baseline correction, denoising, and windowing processing on the vibration event data segments corresponding to the vibration impact characteristic parameters to extract vibration amplitude data and vibration duration data; wherein, the vibration amplitude data includes peak acceleration data and root mean square acceleration data; the vibration duration data includes vibration event duration data and duration data exceeding a preset trigger threshold; S53-4. The vibration duration parameter is compared with a preset duration threshold range to generate a duration determination parameter; S53-5. Frequency domain analysis is performed on the vibration event data segment to extract the dominant frequency component parameter and frequency band energy parameter, and the dominant frequency component parameter and frequency band energy parameter are compared with preset frequency domain determination conditions to generate a frequency domain determination parameter; S53-6. The corresponding vibration event level is determined according to the vibration intensity determination parameter, duration determination parameter, and frequency domain determination parameter, and the hysteresis determination rule is used to maintain the state and suppress the switching of the vibration event level; wherein, the vibration event level includes normal level, slight level, moderate level, and severe level; S53-7. Vibration damage risk assessment parameters are generated according to the vibration event level and preset risk mapping rules.

[0033] Specifically, in this embodiment, step S5 is used to determine the seismic damage status identifier based on vibration monitoring data, so as to characterize the vibration and impact intensity and risk level of the all-welded smart node under seismic vibration and impact load, and to provide input for subsequent node status adjudication. In S51, vibration monitoring data collected by the acceleration sensor is acquired, assuming the three-axis acceleration time histories are as follows: , , The vibration monitoring data is then denoised to obtain the denoised triaxial acceleration signal. , , The triaxial data is synthesized to obtain a synthetic acceleration sequence: ; and based on the trigger threshold The synthesized acceleration sequence is segmented into events to determine the start and end times of each vibration event data segment. and This makes it possible to achieve the following in the interval Internal satisfaction: In step S52, feature extraction is performed on the vibration event data segment to obtain a set of vibration and impact feature parameters. Let the number of samples in the event segment be... The sampling interval is The peak acceleration is: The root mean square acceleration is: The impact duration is: The impact energy is: ; Amplitude spectrum is obtained by performing spectral analysis on the event segment. Then the main frequency component is: This constitutes a set of vibration and impact characteristic parameters: In step S53, vibration damage risk assessment parameters are calculated based on the vibration and impact characteristic parameter set. Each characteristic parameter is normalized to obtain: , Then the parameters for assessing earthquake damage risk. for: ; and the earthquake damage risk assessment parameters The damage status is compared with a preset damage threshold range to generate damage status determination parameters. In S54, a damage status identifier is generated based on the damage status determination parameters, and a threshold is set to meet the specified conditions. The damage status is then classified as follows: normal Minor damage Moderate earthquake damage In case of severe vibration damage, in step S55, a hysteresis determination rule is used to maintain the state and suppress transitions for the vibration damage status indicator. Let the state escalation threshold be... The state degradation threshold is and satisfy ,when When the state is upgraded, it is triggered. Time-triggered state degradation. By introducing a hysteresis interval, state jitter within the threshold neighborhood is suppressed, thereby reducing the probability of misjudgment caused by transient vibration impact and improving the stability and reliability of the vibration damage state output.

[0034] S6: Based on the fusion result of the damage association identifier and the seismic damage status identifier, determine the node status identifier corresponding to the current fully welded smart node.

[0035] Furthermore, step S6 of this application also includes: S61. Obtain the damage association identifier and the seismic damage status identifier, and input the damage association identifier and the seismic damage status identifier into the logic decision module; wherein, the logic decision module is used to perform standardized parsing and unified encoding processing on multi-source status information to form subsequent fusion calculation input parameters; S62. Determine the damage status parameters based on the damage association identifier, and generate damage risk assessment parameters according to the preset damage status mapping rules. Among them, the damage risk assessment parameters Used to characterize the degree of structural damage correlation and map discrete damage states to continuous risk quantification parameters; S63, determine the seismic damage state parameters based on the seismic damage state identifier, and generate seismic damage risk assessment parameters according to the preset seismic damage state mapping rules. Among them, the earthquake damage risk assessment parameters Used to characterize the degree of vibration and impact; S64, based on the damage risk assessment parameters... With the aforementioned earthquake damage risk assessment parameters Constructing a state combination vector ;in: The Used to characterize the enhanced coupling relationship between damage risk and seismic damage risk; S65, input the state combination parameters into the preset node state calculation rules to generate node state parameters. The node state parameters satisfy: ; in, These are node state parameters. For damage risk assessment parameters, For earthquake damage risk assessment parameters, Damage weighting coefficient, For earthquake damage weighting coefficient, This is the coupling enhancement coefficient.

[0036] Specifically, the damage association identifier and the seismic damage status identifier are fused and adjudicated to output node status parameters that can be directly used for operation and maintenance, thereby realizing the mapping from multi-source event judgment results to unified node status results. Further, in step S61, the damage association identifier output in step S4 and the seismic damage status identifier output in step S5 are obtained, and the damage association identifier and the seismic damage status identifier are input into the logic adjudication module; the logic adjudication module is used to uniformly encode and structurally align status information from different sources to form standardized input data required for node status calculation. In step S62, damage status parameters are determined based on the damage association identifier. The damage status parameters include damage level, structural vibration amplitude characteristic parameters, and crack propagation rate parameters. Let the damage level corresponding to the damage association identifier be... Then the damage risk assessment parameters satisfy: ;in, Damage level, These are characteristic parameters of structural vibration amplitude, used to characterize the intensity of structural vibration response. Crack propagation rate is used to characterize the rate of structural damage evolution. A preset damage state mapping function is used to map discrete damage levels and continuous monitoring characteristics into continuous risk assessment parameters. In some embodiments, the vibration amplitude characteristic parameters... This can be expressed as the root mean square value of the acceleration signal: ;in, For structural acceleration response signal, The sampling time window is defined as the crack propagation rate. Used to characterize the rate of change of crack size per unit time, it is expressed as: ;in, In some embodiments, the mapping function is a piecewise mapping method, representing the change of crack characteristic quantities over time. In step S63, the corresponding shock damage state parameters are determined based on the shock damage state identifier, and shock damage risk assessment parameters are generated according to the preset shock damage state mapping rules. Let the damage level corresponding to the damage status indicator be . Then the earthquake damage risk assessment parameters satisfy: ,in, A preset damage state mapping function is used to convert discretized damage levels into continuous risk assessment parameters that can participate in fusion calculations. In some embodiments, the preset damage state mapping function is constructed based on a preset damage grading standard. Specifically, according to the vibration response characteristic parameter ranges corresponding to different damage levels, each damage level is continuously quantified, and a normalized mapping method or a piecewise mapping method is used to establish the correspondence between damage levels and risk assessment parameters, thereby forming the damage state mapping function. The vibration response characteristic parameters include one or more of the following: maximum acceleration, peak displacement, vibration energy, velocity response, or frequency change. In step S64, a combined state parameter is constructed based on the damage state parameters and the vibration damage state parameters. The state combination parameters are used to characterize the joint state relationship between damage risk and seismic damage risk, and they satisfy: ; This serves as a structured composite index for subsequent node state calculations and state tracing analysis. In step S65, the damage risk assessment parameters are... Seismic damage risk assessment parameters and state combination parameters Input the preset node state calculation rules to generate node state parameters. The node state parameters satisfy: ;in, This is the damage weighting coefficient. This is the seismic damage weighting coefficient. This is the coupling enhancement coefficient. Used to characterize the degree of impact of damage risk on node state. Used to characterize the degree of impact of seismic damage risk on node status; This represents a coupling enhancement effect between damage risk and seismic damage risk. In some embodiments, the damage weighting coefficient... Seismic damage weighting coefficient and coupling enhancement coefficient It can be adaptively determined based on the fluctuation characteristics of real-time monitoring data. Specifically, let the fluctuation of the damage risk assessment parameter be... The volatility of the earthquake damage risk assessment parameters is The normalized weight coefficients are defined as follows: ; ;in, This is a preset minimum positive number to avoid a denominator of zero and improve numerical stability. Furthermore, the coupling enhancement coefficient... Defined as: Under normalization constraints, we have: ;in, , , These are used to characterize the contribution weights of damage risk, seismic damage risk, and the coupling enhancement contribution weight between the two, thereby realizing the impact of different risk sources on node state parameters. Adaptive allocation. In some implementations, when damage risk and seismic damage risk increase simultaneously, coupling terms are used to enhance the overall risk response, enabling nodal state parameters to more sensitively reflect the overall structural risk change trend. Further, based on nodal state parameters... The relationship between the node status and a preset node status threshold range generates a node status identifier. Let the preset status thresholds be... and And satisfy ( < If the node status identifier satisfies: Through the above methods, the damage status information and the seismic damage status information are integrated and uniformly expressed, thereby providing a basis for monitoring terminal display, operation and maintenance decision-making, and emergency response strategy generation.

[0037] S7: Determine the corresponding handling strategy based on the node status identifier.

[0038] Specifically, a corresponding handling strategy is generated based on the node status identifier to transform the monitoring results into actionable operation and maintenance suggestions, thereby enabling risk response and management of the fully welded intelligent nodes. The handling strategy can be determined by a preset strategy library or rule table, where the rule table takes the node status identifier as input and a set of handling actions as output. For example, suppose the status level corresponding to the node status identifier is... The handling strategy is Then the handling strategy satisfies: ,in, This is a preset processing mapping rule. In some implementations, when... When the situation is normal, the handling strategy includes continuous monitoring, record archiving, and periodic self-checks; when... When the alert status is active, the response strategy includes issuing an alert, increasing the sampling frequency, triggering encrypted monitoring, and recommending on-site verification and inspection; when When an abnormal state occurs, the handling strategy includes issuing an alarm, triggering an emergency response procedure, recommending immediate repairs and focusing on key nodes for investigation, and recording information such as the occurrence time of the abnormal event, the correlation determination quantity, and the corresponding monitoring zone to support on-site handling. Furthermore, the handling strategy can be correlated with state combination parameters, so that different damage correlation levels and seismic damage levels correspond to different handling priorities and intensity of handling actions, thereby improving the targeting and operability of the handling strategy.

[0039] S8: Send the node status identifier and the handling strategy to the monitoring terminal.

[0040] Specifically, node status identifiers and their corresponding handling strategies are published and presented on the terminal, enabling maintenance personnel to promptly obtain node risk status and handling suggestions, achieving visualization and closed-loop management of monitoring results. Specifically, node status identifiers and handling strategies are encapsulated according to a preset data format to form data packets that the monitoring terminal can parse, and then sent to the monitoring terminal via a communication interface. Let the node status identifier be... , handling strategy Then, sending a data packet can be represented as: ,in, For node identification information, The data packet is sent using a timestamp. After receiving the data packet, the monitoring terminal can display the node status identifier, provide prompts or pop-up alarms for handling strategies, and store historical status and handling records for subsequent traceability and statistical analysis. In some embodiments, the monitoring terminal includes a host computer, a mobile terminal, or a remote monitoring platform; the communication interface includes a wired communication interface and a wireless communication interface; and it can trigger alarm information reporting and log recording when the node status is abnormal, thereby improving the response efficiency and timeliness of operation and maintenance under post-earthquake or impact conditions. This method collects multi-source information such as humidity monitoring, acoustic emission monitoring, and vibration monitoring at the fully welded intelligent node, and combines structural stability analysis, temporal consistency and spatial coupling correlation determination, and event confidence correction to achieve comprehensive identification and graded assessment of humidity anomalies, crack propagation signs, and seismic damage status. It can output node status identifiers more timely and accurately under seismic vibration and impact conditions, and automatically match handling strategies to send to the monitoring terminal, thereby reducing false alarms and missed alarms, improving the efficiency of post-earthquake response and operation and maintenance, and enhancing the safe operation guarantee capability of the fully welded node.

[0041] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0042] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for identifying and treating seismic damage to all-welded joints based on intelligent sensing, characterized in that, The method includes: S1. Obtain the node identification information and structural parameter information of the fully welded intelligent node to be monitored, and determine the sensor installation parameters and monitoring zone parameters based on the structural parameter information to establish the monitoring object model of the fully welded intelligent node; wherein, the structural parameter information includes the welding node's external dimension parameters, wall thickness parameters, and weld position parameters; S2. A humidity sensor, an acoustic emission sensor, and an acceleration sensor are installed at the fully welded intelligent node to collect node operating status data; wherein, the node operating status data includes humidity monitoring data, acoustic emission monitoring data, and vibration monitoring data; S3. A damage monitoring identifier is generated based on the humidity monitoring data and the acoustic emission monitoring data. The damage monitoring identifier includes at least a humidity anomaly identifier and a crack propagation identifier. The humidity anomaly identifier is generated based on the humidity monitoring data, and the crack propagation identifier is generated based on the acoustic emission monitoring data. S4. Extract vibration and impact characteristic parameters based on the vibration monitoring data, analyze the structural stability of the all-welded smart node based on the vibration and impact characteristic parameters, generate a structural stability identifier, and perform correlation analysis based on the structural stability identifier, the humidity anomaly identifier, and the crack propagation identifier to generate a damage correlation identifier. S5. Determine the corresponding vibration damage status indicator based on the vibration monitoring data; S6. Based on the fusion result of the damage association identifier and the seismic damage status identifier, determine the node status identifier corresponding to the current fully welded smart node; S7. Determine the corresponding handling strategy based on the node status identifier; S8. Send the node status identifier and the handling strategy to the monitoring terminal.

2. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 1, characterized in that, A damage monitoring identifier is generated based on the humidity monitoring data and the acoustic emission monitoring data. The damage monitoring identifier includes at least a humidity anomaly identifier and a crack propagation identifier. Specifically, generating the humidity anomaly identifier based on the humidity monitoring data and generating the crack propagation identifier based on the acoustic emission monitoring data includes: S31. Obtain humidity monitoring data collected by the humidity sensor, and filter the humidity monitoring data to extract humidity change amount and humidity change rate parameters. S32. Compare the humidity change amount and humidity change rate parameters with a preset humidity threshold to generate humidity anomaly judgment parameters, and generate the humidity anomaly identifier based on the humidity anomaly judgment parameters; S33. Acquire acoustic emission monitoring data collected by acoustic emission sensor, and extract features from the acoustic emission monitoring data to obtain crack activity feature parameters. The crack activity feature parameters include at least one or more of event count, amplitude, energy, peak frequency or cumulative energy, and generate crack activity identifier. S34. Match the crack activity identifier with the preset crack propagation judgment condition to generate crack propagation judgment parameters, and generate the crack propagation identifier according to the crack propagation judgment parameters.

3. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 1, characterized in that, Vibration and impact characteristic parameters are extracted from the vibration monitoring data. Based on these parameters, the structural stability of the fully welded intelligent node is analyzed, generating a structural stability identifier. Furthermore, a correlation analysis is performed on the structural stability identifier, the humidity anomaly identifier, and the crack propagation identifier to generate a damage correlation identifier, including: S41. Acquire vibration monitoring data collected by the accelerometer, and perform noise reduction and segmentation processing on the vibration monitoring data to extract vibration impact characteristic parameters; wherein, the vibration impact characteristic parameters include at least one or more of peak acceleration, root mean square acceleration, impact duration, dominant frequency component or impact energy. S42. Calculate the structural impact response parameters based on the vibration and impact characteristic parameters. The structural impact response parameters are used to characterize the response intensity and response attenuation characteristics of the all-welded smart node under vibration and impact. S43. Compare the structural impact response parameters with a preset structural stability threshold to generate structural stability judgment parameters, and generate a structural stability identifier based on the structural stability judgment parameters. S44. When both the temporal consistency parameter and the spatial coupling parameter exceed the preset threshold, construct the damage association determination quantity R and generate the damage association identifier.

4. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 3, characterized in that, When both the temporal consistency parameter and the spatial coupling parameter exceed preset thresholds, a damage correlation determination metric R is constructed, and a damage correlation identifier is generated, including: S44-1. Obtain structural stability indicators, humidity anomaly indicators, and crack propagation indicators, and extract the corresponding occurrence time sequences and partition location information respectively; S44-2. Calculate the time offset between the structural stability indicator and the humidity anomaly indicator based on the occurrence time sequence. And according to the time offset Generate timing consistency parameters; S44-3. Calculate the spatial coupling parameter between the crack propagation indicator and the structural stability indicator based on the partition location information. ; S44-4. Construct a damage association determination quantity R based on the temporal consistency parameter and the spatial coupling parameter, generate damage association determination parameters based on the damage association determination quantity R, and generate a damage association identifier based on the damage association determination parameters.

5. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 4, characterized in that, Obtain structural stability indicators, humidity anomaly indicators, and crack propagation indicators, and extract the corresponding occurrence time sequences and partition location information for each: S44-1-1. Unify the time base and correct the timestamps of the event data corresponding to the structural stability marker, humidity anomaly marker and crack propagation marker to generate an event sequence under a unified time scale. S44-1-2. Extract the time sequences of structural stability events, humidity anomaly events, and crack propagation events respectively; S44-1-3. Divide the welding nodes into regions according to the structural size parameters of the welding nodes and the preset zoning rules, and generate monitoring zoning parameters; Map humidity anomaly events and crack propagation events to corresponding partitions to generate partition location information; S44-1-4. Calculate the event confidence parameters of the humidity anomaly indicator and the crack propagation indicator respectively, and generate confidence correction parameters.

6. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 4, characterized in that, Calculate the time offset between the structural stability indicator and the humidity anomaly indicator based on the occurrence time sequence. And according to the time offset Generate timing consistency parameters, including: S44-2-1. Determine the time window parameters for correlation analysis, wherein the time window parameters are determined based on the structural impact response parameters; S44-2-2 Under the constraints of the time window parameters, perform event matching between the time sequence of structural stability events and the time sequence of humidity anomalies to obtain a set of matching event pairs. S44-2-3. Calculate the time offset for the set based on the matching events. and the time offset Normalization is performed to obtain the timing consistency parameters.

7. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 1, characterized in that, Based on the vibration monitoring data, the corresponding vibration damage status indicator is determined, including: S51. Obtain vibration monitoring data collected by the accelerometer, and perform noise reduction, coordinate axis synthesis and segmentation on the vibration monitoring data to obtain vibration event data segments. S52. Perform feature extraction on the vibration event data segment to obtain a vibration impact feature parameter set, wherein the vibration impact feature parameter set includes at least one or more of the following: peak acceleration, root mean square acceleration, impact duration, dominant frequency component, and impact energy. S53. Calculate the vibration and impact characteristic parameter set based on the vibration and impact risk assessment parameters, and compare the vibration and impact risk assessment parameters with the preset vibration and impact threshold range to generate vibration and impact status determination parameters. S54. Generate a vibration damage status identifier based on the vibration damage status determination parameters. The vibration damage status identifier includes at least one of the following: normal, minor vibration damage, moderate vibration damage, and severe vibration damage. S55. The hysteresis judgment rule is used to maintain the state and suppress the switching of the vibration damage status mark, so as to reduce the misjudgment caused by transient vibration impact.

8. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 7, characterized in that, Based on the vibration and impact characteristic parameter set, vibration damage risk assessment parameters are calculated, and these parameters are compared with a preset vibration damage threshold range to generate vibration damage state determination parameters, including: S53-1. Obtain the vibration and impact characteristic parameters, and perform baseline correction, denoising, and windowing processing on the vibration event data segments corresponding to the vibration and impact characteristic parameters to extract vibration amplitude data and vibration duration data; wherein, the vibration amplitude data includes peak acceleration data and root mean square acceleration data; the vibration duration data includes vibration event duration data and duration data exceeding a preset trigger threshold. S53-2. Calculate vibration intensity parameters based on the vibration amplitude data. The vibration intensity parameters include peak intensity parameters and root mean square intensity parameters. Compare the vibration intensity parameters with a preset vibration intensity threshold range to generate vibration intensity judgment parameters. S53-3. Calculate the vibration duration parameter based on the vibration duration data, and compare the vibration duration parameter with a preset duration threshold range to generate a duration determination parameter; S53-4. Perform frequency domain analysis on the vibration event data segment, extract the main frequency component parameters and frequency band energy parameters, and compare the main frequency component parameters and frequency band energy parameters with the preset frequency domain judgment conditions to generate frequency domain judgment parameters. S53-5. Determine the corresponding vibration event level based on the vibration intensity determination parameter, duration determination parameter, and frequency domain determination parameter, and use hysteresis determination rules to maintain the state and suppress switching of the vibration event level; wherein, the vibration event level includes normal level, slight level, moderate level, and severe level; S53-6. Generate vibration damage risk assessment parameters based on the vibration event level and preset risk mapping rules.

9. The method for identifying and treating seismic damage to all-welded joints based on intelligent sensing according to claim 1, characterized in that, Based on the fusion result of the damage association identifier and the seismic damage status identifier, the node status identifier corresponding to the current fully welded smart node is determined, including: S61. Obtain the damage association identifier and the seismic damage status identifier, and input the damage association identifier and the seismic damage status identifier into the logic decision module; wherein, the logic decision module is used to perform standardized parsing and unified encoding processing on multi-source status information to form subsequent fusion calculation input parameters; S62. Determine damage status parameters based on the damage association identifier, and generate damage risk assessment parameters according to preset damage status mapping rules. Among them, the damage risk assessment parameters It is used to characterize the degree of correlation of structural damage and to map discrete damage states into continuous risk quantification parameters; S63. Determine the vibration damage status parameters based on the vibration damage status identifier, and generate vibration damage risk assessment parameters according to the preset vibration damage status mapping rules. Among them, the earthquake damage risk assessment parameters Used to characterize the degree of damage under vibration and impact; S64. Based on the damage risk assessment parameters With the aforementioned earthquake damage risk assessment parameters Constructing a state combination vector ; in: ; The Used to characterize the enhanced coupling relationship between damage risk and seismic damage risk; S65. Input the state combination parameters into the preset node state calculation rules to generate node state parameters. The node state parameters satisfy: ； in, These are node state parameters. For damage risk assessment parameters, For earthquake damage risk assessment parameters, Damage weighting coefficient, For earthquake damage weighting coefficient, This is the coupling enhancement coefficient.

Images