A steel structure deformation intelligent monitoring system

Abstract

The application discloses a steel structure deformation intelligent monitoring system and relates to the technical field of steel structure monitoring.The application solves the problem that the existing monitoring system has a low degree of automation and still needs a large amount of manual intervention in data acquisition, abnormality determination, cause analysis and other links.The application distinguishes between "deformation abnormality" and "misplacement abnormality" of a steel piece through the "trend characteristics" of a resistance change curve of a strain gauge, solves the pain point that only abnormality is known but no cause is known in traditional monitoring, generates a time-resistance curve through resistance change data in a tracing period, and judges the abnormality type of the steel piece through "same trend period / different trend period time length comparison".When the same trend total value is higher, the deformation is determined; and when the different trend total value is higher, the misplacement is determined.The logic based on "data feature backstepping structure state" can not only quickly locate the abnormality, but also directly and explicitly determine the abnormality cause.

Description

Technical Field

[0001] This invention relates to the field of steel structure monitoring technology, specifically to an intelligent monitoring system for steel structure deformation. Background Technology

[0002] Steel structures, with their advantages of high strength, large span, and convenient construction, are widely used in major engineering projects such as high-rise buildings, long-span bridges, industrial plants, and stadiums. However, during long-term service, steel structures are susceptible to cumulative deformation or localized stress concentration due to multiple factors, including load changes (such as the reciprocating load of cranes in industrial plants and the dynamic load of vehicles on bridges), environmental factors (thermal expansion and contraction caused by temperature fluctuations and corrosion caused by humidity), natural disasters (vibrations caused by earthquakes and strong winds), and material aging. If these factors are not detected and addressed in a timely manner, they may lead to safety accidents such as component cracking, connection failure, or even the collapse of the entire structure, posing a serious threat to life and property. Therefore, efficient and accurate deformation monitoring of steel structures is crucial to ensuring their long-term safe service.

[0003] Traditional steel structure deformation monitoring relies heavily on manual inspections and discrete testing methods. Manual inspections involve visually observing the appearance of components and measuring local deformation with simple tools (such as measuring tapes and dial indicators). This is not only inefficient and labor-intensive, but also fails to capture minute stress changes at the micrometer level, easily overlooking early hidden dangers. Discrete testing (such as ultrasonic testing and stress meter sampling) can obtain accurate local data, but it has limitations such as "long detection cycle and limited coverage". It cannot achieve real-time dynamic monitoring of steel structures and cannot reflect the continuous change process of structural stress, resulting in "lag" in monitoring data. This cannot meet the needs of "real-time early warning and timely handling" for large or important steel structure projects.

[0004] With the development of BIM and sensing technologies, some monitoring solutions have begun to incorporate tools such as strain gauges and BIM models. However, significant technical shortcomings remain: Firstly, existing solutions often focus on stress monitoring at single contact points, lacking correlation analysis between "contact point - related components - overall steel structure." This often leads to the problem of "handling individual anomalies separately while ignoring overall structural stress anomalies." For example, only addressing stress exceeding limits at a single contact point may fail to detect overall displacement in the steel structure associated with that point, resulting in incomplete elimination of potential hazards. Secondly, even if anomalies are identified, existing solutions struggle to accurately determine the type of anomaly (e.g., whether it's deformation or misalignment). Complex subsequent inspections by maintenance personnel are required to determine the cause, prolonging the "anomaly discovery - problem resolution" cycle and increasing structural safety risks. Furthermore, existing monitoring systems have low automation levels. Data acquisition, anomaly detection, and cause analysis still require significant manual intervention. This not only easily leads to human error affecting monitoring accuracy but also results in low maintenance efficiency, making it difficult to meet the long-term, continuous monitoring needs of large steel structure projects.

[0005] Therefore, there is an urgent need for a fully intelligent monitoring system that can achieve "real-time monitoring, accurate identification of anomalies, location of abnormal steel components, and analysis of anomaly types" to overcome the limitations of traditional monitoring methods and provide scientific and efficient technical support for the safe operation and maintenance of steel structures. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides an intelligent monitoring system for steel structure deformation, which solves the problems of low automation levels and the need for extensive manual intervention in data acquisition, anomaly detection, and cause analysis in existing monitoring systems.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring system for steel structure deformation, comprising: At the node parameter monitoring end, strain gauges are set at different steel structure contact points to monitor the stress data associated with the steel structure contact points in real time, and the real-time monitored stress data is transmitted to the stress characteristic analysis end. On the stress characteristic analysis end, based on the relevant parameters associated with the corresponding steel structure contact points within the preset correlation model, the stress data of each steel structure contact point is confirmed. Using the confirmed stress data as a baseline interval, the monitored stress data is checked for anomalies, and the calibration process for abnormal contact points is initiated. The specific method is as follows: The stress data associated with the corresponding steel structure contact points are labeled YL. i Where i represents different steel structure contact points, then lock the associated contact points from the preset associated model, use them as reference points, and confirm the force data associated with the reference points: lock the axial pressure and cross-sectional area of ​​the force-bearing surface associated with the reference points, and use: axial pressure ÷ cross-sectional area = axial force to confirm the axial force associated with the reference points. Extract the bending moment associated with the reference point and the moment of inertia of the associated beam, and then extract the distance L of the reference point relative to the neutral axis. i The formula is: (bending moment × moment of inertia) ÷ L i = Bending moment force, confirm the bending moment force associated with the reference point; Extract the shear force transmitted from the associated beam end to the reference point, and simultaneously confirm the cross-sectional area of ​​the associated beam end. Use the formula: shear force ÷ cross-sectional area = reference shear force to confirm the reference shear force associated with the reference point. Add the axial force and bending moment associated with the reference point to determine the superimposed force, and then determine the superimposed force L1 associated with the reference point. i and the reference shear force L2 i Identify the baseline interval, and denote the minimum value of the baseline interval as ZJ. i min, the maximum value is denoted as ZJ i max, using: ; Monitoring the YL associated with the corresponding steel structure contact points i Whether it is within the reference range, if so, it represents the stress data YL monitored at the corresponding steel structure contact point. i No abnormalities are found, which is within the normal range. Otherwise, it indicates that the stress data YL monitored at the corresponding steel structure contact point is within the normal range. i If an anomaly is found, the corresponding steel structure contact point will be marked as an abnormal contact point. At the selected end of the model unit, based on the marked abnormal contact points, the model unit associated with the abnormal contact points is identified, and other contact points of the model unit are evaluated for abnormality to lock the abnormal steel component. The specific method is as follows: Based on the marked abnormal contact points, the individual steel components associated with the abnormal contact points are confirmed within the preset association model. Then, a set of monitoring cycles is executed, which is the preset monitoring cycle. Other contact points of different individual steel components are recorded as points to be identified. Within the monitoring cycle, it is confirmed whether the stress data of other points to be identified is abnormal. If so, the corresponding points to be identified are recorded as abnormal contact points. If not, no marking is required. If there is no stress data abnormality at all points to be identified, an error signal is generated and displayed directly. Individual steel components with all surrounding contact points being abnormal contact points are recorded as abnormal steel components, and the confirmed abnormal steel components are transmitted to the associated data analysis terminal. The associated data analysis end extracts the resistance change data generated by the strain gauges at different contact points of the abnormal steel parts, confirms the change characteristics associated with different resistance change data, performs comprehensive verification of multiple sets of change characteristics, and generates verification signals based on the verification results for display. Preferably, the specific method for confirming the change characteristics in the associated data analysis terminal is as follows: Taking the current moment as the initial moment, a set of traceability cycles is confirmed. The traceability cycle is a preset cycle. The resistance change data generated by the strain gauges associated with different contact points of the abnormal steel parts within the traceability cycle is confirmed, and the resistance change curve associated with the strain gauges is directly generated. In the resistance change curves associated with different strain gauges, the change characteristics of adjacent points are identified. The resistance data of the point after the adjacent point is designated as Z1, and the resistance data of the point before the adjacent point is designated as Z2. The change characteristic is (Z1-Z2). The change characteristics associated with adjacent points in the different resistance change curves are then identified in turn.

[0008] Preferably, the specific method for comprehensively verifying multiple sets of change characteristics in the associated data analysis terminal is as follows: From the different resistance change curves associated with different strain gauges, locate the curve point with the largest difference from the standard resistance value Zr, and mark it in the corresponding resistance change curve as the mark point, where Zr is the preset standard resistance value. The time associated with different marker points is recorded as the marker time, and the time period associated with multiple marker time periods is recorded as the processing time period. The marker points associated with different resistance change curves are moved back and forth within the processing time period, and the movement process is recorded. The same trend within the same time period is confirmed: different marker points are randomly moved to designated positions within the processing time period, and multiple curve segments associated with each other within the processing time period are verified. It is determined whether the change characteristics associated with adjacent points are all positive or negative. If so, the time period between the corresponding adjacent points is recorded as a period of the same trend; otherwise, it is recorded as a period of different trends. The durations of the same-trend and different-trend periods are compared. If the period of the same trend is relatively long, the current movement is recorded as the same trend process, and the duration of the confirmed same trend period is recorded as the process characteristic of the same trend process. If the time periods of the opposite trend intersect, the current movement process is recorded as the opposite trend process, and the duration of the confirmed opposite trend period is recorded as the process characteristic of the opposite trend process. Divide several moving processes into processes with the same trend or processes with different trends. Summate the process characteristics of processes with the same trend and record them as the sum of the same trend. Then sum the process characteristics of processes with different trends and record them as the sum of the different trends. If the sum of values ​​with the same trend is greater than the sum of values ​​with different trends, then a deformation signal for the steel component is generated. If the sum of values ​​with the same trend is less than the sum of values ​​with different trends, a steel component misalignment signal is generated. If the sum of values ​​with the same trend equals the sum of values ​​with different trends, an error signal is generated directly.

[0009] This invention provides an intelligent monitoring system for steel structure deformation. Compared with existing technologies, it has the following advantages: This invention uses the benchmark data (calculated values ​​of axial force, bending moment, and shear force) in a pre-defined associated model as its core to construct a judgment system of "benchmark interval - measured data comparison," rather than relying on a single threshold for simple judgment. On the one hand, by calculating axial force, bending moment, and shear force step by step and deriving superimposed forces, the benchmark interval is made to better reflect the actual stress characteristics of steel structure contact points, avoiding abnormal omissions or mislabeling caused by "misjudgment of a single force parameter." On the other hand, by combining the stress conditions of contact points associated with the BIM model, the matching degree between measured data and theoretical forces is further verified, ensuring the scientific validity of abnormal contact point calibration. By analyzing the "trend characteristics" of strain gauge resistance change curves, the system distinguishes between "deformation anomalies" and "misalignment anomalies" in steel components, addressing the pain point of traditional monitoring that "only knows the anomaly, but not its cause." The system generates a time-resistance curve from resistance change data within a traceability period and determines the type of anomaly by comparing the duration of periods with and without the same trend: a higher sum of values ​​for the same trend indicates deformation, while a higher sum of values ​​for different trends indicates misalignment. This logic, based on "inferring structural state from data characteristics," not only quickly locates anomalies but also directly identifies their causes. Attached Figure Description

[0010] Figure 1 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] First Embodiment Please see Figure 1 This application provides an intelligent monitoring system for steel structure deformation, including a node parameter monitoring end, a stress characteristic analysis end, a model unit selection end, and a correlation data analysis end. The node parameter monitoring end and the stress characteristic analysis end are electrically connected to the input node, and the stress characteristic analysis end, the model unit selection end, and the correlation data analysis end are electrically connected sequentially from the output node to the input node. Among them, the node parameter monitoring end sets up associated strain gauges at different steel structure contact points to monitor the stress data associated with the steel structure contact points in real time, and transmits the real-time monitored stress data to the stress characteristic analysis end. Specifically, the core component inside the strain gauge is a metal sensitive grid. When the steel structure component is subjected to forces such as tension, compression, and bending moment, it will produce slight elongation, shortening, or bending deformation. The strain gauge attached to the surface of the component will deform synchronously with the component. Based on the resistance change process generated during the corresponding deformation, the specific change of the corresponding stress can be confirmed. In the stress characteristic analysis section, based on the relevant parameters associated between the corresponding steel structure contact points in the preset correlation model, the stress data of each steel structure contact point is confirmed. Using the confirmed stress data as a benchmark range, the abnormality of the monitored stress data is confirmed, and the calibration process of abnormal contact points is carried out. Specifically, the stress data of the corresponding contact points in the preset correlation model is used as the benchmark data. Subsequently, based on this benchmark data, it is used to evaluate whether there is a large error in the data during the actual monitoring process. If the error is too large, it means that there is a related problem at the corresponding contact point. If the error is small, it means that there is no related problem at the corresponding contact point, and there is no need to perform specific calibration of abnormal contact points. The specific method for calibrating abnormal contact points is as follows: The stress data associated with the corresponding steel structure contact points are labeled YL. i Where i represents different steel structure contact points, then lock the associated contact points from the preset associated model, use them as reference points, and confirm the force data associated with the reference points: lock the axial pressure and cross-sectional area of ​​the force-bearing surface associated with the reference points, and use: axial pressure ÷ cross-sectional area = axial force to confirm the axial force associated with the reference points. Extract the bending moment associated with the reference point and the moment of inertia of the associated beam, and then extract the distance L of the reference point relative to the neutral axis. i The formula is: (bending moment × moment of inertia) ÷ L i = Bending moment force, confirm the bending moment force associated with the reference point; Extract the shear force transmitted from the associated beam end to the reference point, and simultaneously confirm the cross-sectional area of ​​the associated beam end. Use the formula: shear force ÷ cross-sectional area = reference shear force to confirm the reference shear force associated with the reference point. Add the axial force and bending moment associated with the reference point to determine the superimposed force, and then determine the superimposed force L1 associated with the reference point. i and the reference shear force L2 i Identify the baseline interval, and denote the minimum value of the baseline interval as ZJ. i min, the maximum value is denoted as ZJ i max, using: ; Monitoring the YL associated with the corresponding steel structure contact points i Whether it is within the reference range, if so, it represents the stress data YL monitored at the corresponding steel structure contact point. i No abnormalities are found, which is within the normal range. Otherwise, it indicates that the stress data YL monitored at the corresponding steel structure contact point is within the normal range. i If an anomaly is found, the corresponding steel structure contact point will be marked as an abnormal contact point. Specifically, there is associated stress data for each steel structure contact point. Combined with the specific BIM steel structure model, the stress condition of each contact point can be confirmed. The associated data is selected from the corresponding model to confirm the different forces in the contact process. Based on the confirmed different forces, the corresponding numerical range is determined to monitor whether the actual data monitored for the corresponding contact point meets the error standard. If it meets the standard, it means that the corresponding contact point is in a normal contact state. Otherwise, it is in an abnormal contact state and needs to be marked as an abnormal contact point. Subsequently, based on the confirmed abnormal contact points, the associated components are re-analyzed to identify the stress state of other contact points of the corresponding components, thereby analyzing whether the corresponding components have deformation characteristics and displaying signals in a timely manner.

[0013] Second Embodiment In the model unit selection end, based on the marked abnormal contact points, the model unit associated with the abnormal contact points is identified, and the abnormality assessment of other contact points of the model unit is performed to lock the abnormal steel parts. Specifically, when a certain steel part has an abnormality, its contact points are not only abnormal, but other contact points will also become abnormal in sync. Then such steel parts are considered to be problematic steel parts, and it is necessary to identify whether the corresponding problematic steel parts have experienced related offsets or deformations. The specific method for locking abnormal steel components is as follows: Based on the marked abnormal contact points, the associated individual steel components within the preset correlation model are confirmed. Then, a set of monitoring cycles is executed. The monitoring cycle is a preset cycle, determined in advance by the operator based on experience, generally set to 1 minute. Other contact points of different individual steel components are recorded as points to be identified. Within the monitoring cycle, it is confirmed whether the stress data of other points to be identified is abnormal. If so, the corresponding points to be identified are simultaneously recorded as abnormal contact points. If not, no marking is required. If there is no abnormal stress data at all points to be identified, an error signal is directly generated and displayed (this may be caused by strain gauge damage, requiring manual intervention). Individual steel components with all surrounding contact points being abnormal contact points are recorded as abnormal steel components. The confirmed abnormal steel components are then transmitted to the associated data analysis terminal. Subsequently, the stress data associated with the abnormal steel components needs to be analyzed to identify what kind of abnormality the steel component is in. The abnormality includes offset abnormality or deformation abnormality, and the stress data change characteristics associated with the two are inconsistent.

[0014] Among them, the associated data analysis end extracts the resistance change data generated by the strain gauges at different contact points of abnormal steel parts, confirms the change characteristics associated with different resistance change data, performs comprehensive verification of multiple sets of change characteristics, and generates verification signals based on the verification results for display. The specific methods for confirming the characteristics of change are as follows: Starting from the current moment, a set of traceability cycles is confirmed. The traceability cycle is a preset cycle, generally 3 minutes, which is the past 3 minutes. The resistance change data of the strain gauges associated with different contact points of the abnormal steel parts during the traceability cycle are confirmed, and the resistance change curve associated with the strain gauges is directly generated. The horizontal axis of the curve is the time line, and the vertical axis is the resistance value. In the resistance change curves associated with different strain gauges, the change characteristics of adjacent points are identified. The resistance data of the point after the adjacent point is designated as Z1, and the resistance data of the point before the adjacent point is designated as Z2. The change characteristic is (Z1-Z2). The change characteristics associated with adjacent points in the different resistance change curves are then identified in turn. The specific method for comprehensively verifying multiple sets of change characteristics is as follows: From the different resistance change curves associated with different strain gauges, locate the curve point with the largest difference from the standard resistance value Zr, and mark it in the corresponding resistance change curve as the mark point. Its Zr is the preset standard resistance value, which is the resistance value when the monitored strain data is in the 0 state. The time associated with different marker points is recorded as the marker time, and the time period associated with multiple marker time periods is recorded as the processing time period. The marker points associated with different resistance change curves are moved back and forth within the processing time period, and the movement process is recorded. The same trend within the same time period is confirmed: different marker points are randomly moved to designated positions within the processing time period, and multiple curve segments associated with each other within the processing time period are verified. It is determined whether the change characteristics associated with adjacent points are all positive or negative. If so, the time period between the corresponding adjacent points is recorded as a period of the same trend; otherwise, it is recorded as a period of different trends. The durations of the same-trend and different-trend periods are compared. If the period of the same trend is relatively long, the current movement is recorded as the same trend process, and the duration of the confirmed same trend period is recorded as the process characteristic of the same trend process. If the time periods of the opposite trend intersect, the current movement process is recorded as the opposite trend process, and the duration of the confirmed opposite trend period is recorded as the process characteristic of the opposite trend process. Divide several moving processes into processes with the same trend or processes with different trends. Summate the process characteristics of processes with the same trend and record them as the sum of the same trend. Then sum the process characteristics of processes with different trends and record them as the sum of the different trends. If the sum of the same trend values ​​is greater than the sum of the opposite trend values, a deformation signal for the steel component is generated (during deformation, the strain gauges on both sides move relative to each other, that is, they move towards the middle at the same time, so both are relatively loose, and the resistance changes of the two strain gauges have the same trend, which is the deformation process). If the sum of the same trend values ​​is less than the sum of the opposite trend values, a steel component misalignment signal is generated (when misaligned, both sides will change synchronously, and their resistance changes in a relatively consistent manner). If the sum of values ​​with the same trend equals the sum of values ​​with different trends, an error signal will be generated directly (this situation is almost never seen, but if it does occur, it requires manual detection).

[0015] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0016] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A smart monitoring system for steel structure deformation, characterized in that, include: At the node parameter monitoring end, strain gauges are set at different steel structure contact points to monitor the stress data associated with the steel structure contact points in real time, and the real-time monitored stress data is transmitted to the stress characteristic analysis end. The stress characteristic analysis end confirms the stress data of each steel structure contact point based on the relevant parameters associated between the corresponding steel structure contact points in the preset correlation model. Using the confirmed stress data as the benchmark interval, it confirms whether the monitored stress data is abnormal and performs the calibration process for abnormal contact points. Once the model unit is selected, the model unit associated with the marked abnormal contact point is identified, and other contact points of the model unit are evaluated for abnormality to lock the abnormal steel component. The associated data analysis module extracts resistance change data generated by strain gauges at different contact points of abnormal steel components, confirms the associated change characteristics of different resistance change data, comprehensively verifies multiple sets of change characteristics, and generates and displays a verification signal based on the verification results. The specific method is as follows: Taking the current moment as the initial moment, a set of traceability cycles is confirmed. The traceability cycle is a preset cycle. The resistance change data generated by the strain gauges associated with different contact points of the abnormal steel parts within the traceability cycle is confirmed, and the resistance change curve associated with the strain gauges is directly generated. In the resistance change curves associated with different strain gauges, the change characteristics of adjacent points are identified. The resistance data of the point after the adjacent point is designated as Z1, and the resistance data of the point before the adjacent point is designated as Z2. The change characteristic is (Z1-Z2). The change characteristics associated with adjacent points in the different resistance change curves are then identified in turn. The specific method for comprehensively verifying multiple sets of change characteristics is as follows: From the different resistance change curves associated with different strain gauges, locate the curve point with the largest difference from the standard resistance value Zr, and mark it in the corresponding resistance change curve as the mark point, where Zr is the preset standard resistance value. The time associated with different marker points is recorded as the marker time, and the time period associated with multiple marker time periods is recorded as the processing time period. The marker points associated with different resistance change curves are moved back and forth within the processing time period, and the movement process is recorded. The same trend within the same time period is confirmed: different marker points are randomly moved to designated positions within the processing time period, and multiple curve segments associated with each other within the processing time period are verified. It is determined whether the change characteristics associated with adjacent points are all positive or negative. If so, the time period between the corresponding adjacent points is recorded as a period of the same trend; otherwise, it is recorded as a period of different trends. The durations of the same-trend and different-trend periods are compared. If the period of the same trend is relatively long, the current movement is recorded as the same trend process, and the duration of the confirmed same trend period is recorded as the process characteristic of the same trend process. If the period of an anomaly is long, the current movement is recorded as the anomaly process, and the duration of the confirmed anomaly period is recorded as the process characteristic of the anomaly process. Divide several moving processes into processes with the same trend or processes with different trends. Summate the process characteristics of processes with the same trend and record them as the sum of the same trend. Then sum the process characteristics of processes with different trends and record them as the sum of the different trends. If the sum of values ​​with the same trend is greater than the sum of values ​​with different trends, then a deformation signal for the steel component is generated.

2. The intelligent monitoring system for steel structure deformation according to claim 1, characterized in that, The specific method for calibrating abnormal contact points in the force characteristic analysis terminal is as follows: marking stress data associated with the steel structure contact point as YL i wherein i represents different steel structure contact points, locking the associated contact point from the preset correlation model as a reference point, and confirming the stress data associated with the reference point: locking the axial pressure and the cross-sectional area of the stress surface associated with the reference point, using: axial pressure ÷ cross-sectional area = axial force, confirming the axial force associated with the reference point; Extract the bending moment associated with the reference point and the moment of inertia of the associated beam, and then extract the distance L of the reference point relative to the neutral axis. i The formula is: (bending moment × moment of inertia) ÷ L i = Bending moment force, confirm the bending moment force associated with the reference point; Extract the shear force transmitted from the associated beam end to the reference point, and simultaneously confirm the cross-sectional area of ​​the associated beam end. Use the formula: shear force ÷ cross-sectional area = reference shear force to confirm the reference shear force associated with the reference point. Add the axial force and bending moment associated with the reference point to determine the superimposed force, and then determine the superimposed force L1 associated with the reference point. i and the reference shear force L2 i Identify the baseline interval, and denote the minimum value of the baseline interval as ZJ. i min, the maximum value is denoted as ZJ i max, using: ; Monitoring the YL associated with the corresponding steel structure contact points i Whether it is within the reference range, if so, it represents the stress data YL monitored at the corresponding steel structure contact point. i No abnormalities were found; the result is within the normal range.

3. The intelligent monitoring system for steel structure deformation according to claim 2, characterized in that, If YL i If it is not within the reference range, it represents the stress data YL monitored at the corresponding steel structure contact point. i If an anomaly is found, the corresponding steel structure contact point will be marked as an abnormal contact point.

4. The intelligent monitoring system for steel structure deformation according to claim 1, characterized in that, The specific method for locking abnormal steel components at the selected end of the model unit is as follows: Based on the marked abnormal contact points, the individual steel components associated with the abnormal contact points are confirmed within the preset association model. Then, a set of monitoring cycles is executed, which is the preset monitoring cycle. Other contact points of different individual steel components are recorded as points to be identified. Within the monitoring cycle, it is confirmed whether the stress data of other points to be identified is abnormal. If so, the corresponding points to be identified are recorded as abnormal contact points. If not, no marking is required. If there is no stress data abnormality at all points to be identified, an error signal is generated and displayed directly. Individual steel components whose surrounding contact points are all abnormal are recorded as abnormal steel components, and the confirmed abnormal steel components are transmitted to the associated data analysis terminal.

5. The intelligent monitoring system for steel structure deformation according to claim 1, characterized in that, If the sum of values ​​with the same trend is less than the sum of values ​​with different trends, a steel component misalignment signal is generated.

6. The intelligent monitoring system for steel structure deformation according to claim 1, characterized in that, If the sum of values ​​with the same trend equals the sum of values ​​with different trends, an error signal is generated directly.

Images