Intelligent monitoring system for deformation of steel structure

Abstract

The invention discloses an intelligent monitoring system for deformation of a steel structure, relates to the technical field of steel structure monitoring, and solves the problems that an existing monitoring system is relatively low in automation degree, and links such as data acquisition, abnormality judgment and cause analysis still need a large amount of manual intervention. Deformation abnormity and dislocation abnormity of the steel part are distinguished, and the pain point that only abnormity is known, and causes of formation are not known in traditional monitoring is solved; a time-resistance curve is generated through resistance change data in a tracing period, and the abnormal type of the steel part is judged through'same-trend time period / different-trend time period duration comparison ': when the same-trend sum value is higher, deformation is judged, and when the different-trend sum value is higher, dislocation is judged; the logic based on the'data feature backstepping structure state 'not only can quickly position the exception, but also can directly determine the cause of the exception.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of steel structure monitoring, in particular to a steel structure deformation intelligent monitoring system. BACKGROUND

[0002] Steel structures are widely used in major engineering fields such as high-rise buildings, long-span bridges, industrial plants, stadiums, etc. due to their high strength, large span, and convenient construction. However, during long-term service, steel structures are easily affected by multiple factors such as load changes (e.g. industrial plant crane reciprocating load, bridge vehicle dynamic load), environmental factors (thermal expansion and contraction caused by temperature fluctuations, corrosion caused by humidity), natural disasters (vibration caused by earthquakes and strong winds), and material aging, which may cause cumulative deformation or local stress concentration. If not discovered and addressed in a timely manner, it may lead to component cracking, connection failure, or even overall structure collapse, posing a serious threat to life and property safety. Therefore, efficient and accurate deformation monitoring of steel structures is crucial to ensure their long-term safe service.

[0003] Traditional steel structure deformation monitoring relies on manual inspection and discrete detection methods: manual inspection observes the appearance of components by eye and measures local deformation with simple tools (such as tape measure, dial gauge), which is not only inefficient and labor-intensive, but also difficult to capture micron-level minor stress changes, easily missing early hidden problems; discrete detection (such as ultrasonic flaw detection, stress meter sampling) can obtain local accurate data, but has limitations such as "long detection cycle, limited coverage", which cannot achieve real-time dynamic monitoring of steel structures, making it difficult to reflect the continuous change process of structural stress, resulting in "lag" in monitoring data, which cannot meet the needs of real-time early warning and timely disposal for large or important steel structure projects.

[0004] With the development of BIM technology and sensing technology, some monitoring solutions have introduced strain gauges and BIM models, but there are still obvious technical shortcomings: on the one hand, existing solutions focus on stress monitoring at a single contact point, lack of correlation analysis of "contact point-associated component-entire steel piece", often resulting in problems such as "single-point abnormality handled separately, ignoring overall stress abnormality of components", for example, only handling stress exceeding limits at a certain contact point, but not discovering overall displacement of the steel piece to which the contact point belongs, resulting in incomplete elimination of hidden dangers; on the other hand, even if existing solutions identify abnormalities, it is difficult to accurately determine the type of abnormality (such as deformation or misplacement of steel pieces), which requires subsequent complex detection by maintenance personnel to determine the cause, prolonging the "abnormality discovery-problem solving" cycle and increasing the risk of structural safety. In addition, the existing monitoring system has low automation, and data collection, abnormality determination, and cause analysis still require a lot of manual intervention, which not only affects the monitoring accuracy due to human operation errors, but also leads to low efficiency of maintenance, making it difficult to adapt to the long-term and continuous monitoring needs of large steel structure projects.

[0005] Therefore, there is an urgent need for a full-process intelligent monitoring system that can realize "real-time monitoring, accurate exception identification, exception steel part positioning, and exception type research and judgment" to solve the limitations of traditional monitoring methods and provide scientific and efficient technical support for steel structure safety operation and maintenance. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a steel structure deformation intelligent monitoring system, which solves the problem that the existing monitoring system has a low degree of automation, and data acquisition, exception determination, and cause analysis still require a large amount of manual intervention.

[0007] To achieve the above object, the present application is implemented by the following technical scheme: a steel structure deformation intelligent monitoring system, comprising: A node parameter monitoring end is provided at different steel structure contact points, associated strain gauges are arranged, the stress data associated with the steel structure contact points are monitored in real time, and the real-time monitored stress data are transmitted to the stress characteristic analysis end; The stress characteristic analysis end confirms the stress data of each steel structure contact point according to the relevant parameters associated with the corresponding steel structure contact points in the preset associated model, and confirms whether the monitored stress data are abnormal based on the confirmed stress data as the reference interval, and carries out the calibration process of the abnormal contact point, in particular: The stress data associated with the corresponding steel structure contact points are marked as YL i , wherein i represents different steel structure contact points, and the associated contact points are locked from the preset associated model and taken as reference points, and the stress data associated with the reference points are confirmed: the axial pressure and the cross-sectional area of the stress surface associated with the reference points are locked, and the axial force is confirmed by using: axial pressure ÷ cross-sectional area = axial force; The bending moment associated with the reference point and the moment of inertia of the associated beam are extracted, and the distance L i of the reference point relative to the neutral axis is extracted, and the bending moment force associated with the reference point is confirmed by using: (bending moment × moment of inertia) ÷ L i ; The shear force transmitted to the reference point from the end of the associated beam is extracted, and the cross-sectional area of the end of the associated beam is confirmed synchronously, and the reference shear force associated with the reference point is confirmed by using: shear force ÷ cross-sectional area = reference shear force; The axial force and the bending moment force associated with the reference point are added to determine the superimposed force, and the reference interval is confirmed according to the superimposed force L1 i associated with the reference point and the reference shear force L2 i , the minimum value of the reference interval is recorded as ZJ i min, and the maximum value is recorded as ZJ i max, and the following is used: ; monitoring YL corresponding to the contact point of the steel structure i whether it is in the reference interval, if so, it represents the stress data YL monitored by the corresponding contact point of the steel structure i no exception, within the normal range, if not, it represents the stress data YL monitored by the corresponding contact point of the steel structure i there is an abnormality, and the corresponding steel structure contact point is directly marked as an abnormal contact point; model monomer selection end, according to the marked abnormal contact point, confirm the model monomer associated with the abnormal contact point, and evaluate the other contact points of the model monomer, lock the abnormal steel piece, the specific way is: According to the marked abnormal contact point, the monomer steel piece associated with the abnormal contact point is confirmed again, and a group of monitoring cycles is executed, the monitoring cycle is the preset cycle, and the other contact points of different monomer steel pieces are recorded as to be identified points. In the monitoring cycle, it is confirmed whether the stress data of the other to-be-identified points is abnormal, if so, the corresponding to-be-identified point is marked as an abnormal contact point, if not, no marking is needed, if all to-be-identified points do not exist stress data abnormality, then directly generate error signal display; The monomer steel piece with all surrounding contact points as abnormal contact points is recorded as abnormal steel piece, and the confirmed abnormal steel piece is transmitted to the associated data analysis end; associated data analysis end, extract the resistance value change data generated by the strain gauge associated with the different contact points of the abnormal steel piece, and confirm the change characteristics associated with the different resistance value change data, and the change characteristics are verified comprehensively, and the verification signal is generated according to the verification result for display; Preferably, the associated data analysis end, the specific way of confirming the change characteristics is: Take the current time as the initial time, confirm a group of tracing periods, the tracing period is the preset period, confirm the resistance value change data generated by the strain gauge associated with the different contact points of the abnormal steel piece in the tracing period, and directly generate the resistance value change curve associated with the strain gauge; In different resistance value change curves associated with different strain gauges, confirm the change characteristics of adjacent points, and the resistance value data of the next point after the adjacent point is Z1, and the resistance value data of the previous point is Z2, and the change characteristics = (Z1-Z2), and the change characteristics associated with the adjacent points in different resistance value change curves are confirmed in turn.

[0008] Preferably, the associated data analysis end, the specific way of comprehensively verifying a plurality of change characteristics is: From different resistance value change curves associated with different strain gauges, lock the curve point with the largest distance standard resistance value Zr difference, and mark it in the corresponding resistance value change curve, marked as a marker, and Zr is a preset standard resistance value; The time points associated with different marking points are recorded as marking time points, the time period associated with multiple marking time periods is recorded as a to-be-processed time period, the marking points associated with different resistance value change curves are moved forward and backward in the to-be-processed time period, and the moving process is recorded, the same trend in the same period is confirmed, the marking points are randomly moved to the specified position of the to-be-processed time period, the multiple partial curve segments associated in the to-be-processed time period are checked, and whether the change characteristics associated between adjacent point positions are all positive or negative values is identified, if yes, the time period between the corresponding adjacent point positions is recorded as a same trend time period, otherwise, it is recorded as a different trend time period, and the length of the same trend time period or the different trend time period is compared: If the same trend time period is relatively long, the current moving process is recorded as a same trend process, and the length of the same trend time period confirmed is recorded as the process characteristic of the same trend process; If the different trend time period is crossed, the current moving process is recorded as a different trend process, and the length of the different trend time period confirmed is recorded as the process characteristic of the different trend process; The same trend process or the different trend process is divided for a plurality of moving processes, the process characteristics of the same trend processes are summed up and recorded as a same trend total value, and the process characteristics of the different trend processes are summed up and recorded as a different trend total value; If the same trend total value is greater than the different trend total value, a steel piece deformation signal is generated; If the same trend total value is less than the different trend total value, a steel piece dislocation signal is generated; If the same trend total value is equal to the different trend total value, an error signal is directly generated.

[0009] The application provides a steel structure deformation intelligent monitoring system. Compared with the prior art, the application has the following beneficial effects: The application takes the reference data (axial force, bending moment force and shear force calculation value) in the preset correlation model as the core to construct a determination system of "reference interval-real measurement data comparison", instead of simple determination by relying on a single threshold value. On the one hand, through step-by-step calculation and superimposed force derivation of the axial force, bending moment force and shear force, the reference interval is more in line with the actual stress characteristics of the contact point of the steel structure, and abnormal missing or mislabeling caused by "single force parameter misjudgment" is avoided. On the other hand, in combination with the force condition of the contact point associated with the BIM model, the matching degree of the measured data and the theoretical stress is further verified to ensure the scientificity of the abnormal contact point labeling; By the "trend characteristics" of the resistance change curve of the strain gauge, the "deformation anomaly" and the "misplacement anomaly" of the steel member are distinguished, and the pain point of "only knowing the anomaly, not knowing the cause" in the traditional monitoring is solved. The system generates a time-resistance curve by tracing the resistance change data in the period, and judges the type of the steel member anomaly by "same trend period / different trend period length comparison": when the same trend total value is higher, it is determined as deformation, and when the different trend total value is higher, it is determined as misplacement. This logic based on "data feature backstepping structure state" can not only quickly locate the anomaly, but also directly and clearly determine the cause of the anomaly. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 The figure is a schematic diagram of the principle framework of the application. DETAILED DESCRIPTION

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

[0012] First embodiment Please refer to Figure 1 The application provides a steel structure deformation intelligent monitoring system, which comprises a node parameter monitoring end, a stress characteristic analysis end, a model single selection end and a related 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 single selection end and the related data analysis end are electrically connected to the output node and the input node in sequence. The node parameter monitoring end is provided with related strain gauges at different steel structure contact points, and the stress data associated with the steel structure contact points are monitored in real time, and the real-time monitored stress data are transmitted to the stress characteristic analysis end. Specifically, the internal core component of the strain gauge is a metal sensitive grid. When the steel structure member is subjected to tension, pressure, bending moment and other forces, it will produce slight elongation, shortening or bending deformation. The strain gauge pasted on the surface of the member will deform synchronously with the member. According to the resistance change process in the corresponding deformation process, the specific change of the corresponding stress is 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 specifically calibrate the 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, corresponding to the steel structure contact point, there is associated stress data, 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, so as to confirm the different forces in the contact process, and then according to the confirmed different forces, the corresponding numerical interval is confirmed, so as to monitor whether the actual data monitored by the corresponding contact point is error standard, if it is, it means that the corresponding contact point belongs to the state of normal contact, otherwise, it belongs to the state of abnormal contact, which needs to be calibrated as an abnormal contact point; Then, according to the confirmed abnormal contact point, the associated component is reanalyzed, the stress state of other contact points of the corresponding component is identified, so as to analyze whether the corresponding component has deformation characteristics, and timely signal display is performed.

[0013] Second embodiment Among them, the model monomer selected end confirms the model monomer associated with the abnormal contact point according to the marked abnormal contact point, and performs abnormal evaluation on other contact points of the model monomer, and locks the abnormal steel piece. Specifically, when a certain steel piece is abnormal, its contact points are not only single abnormal, and other contact points will also synchronously follow abnormal, then such steel piece belongs to the steel piece with problems, and it is necessary to identify whether the corresponding problem steel piece has related deviation or deformation; Among them, the specific way of locking the abnormal steel piece is: According to the marked abnormal contact point, the monomer steel piece associated with the abnormal contact point in the associated model is pre-set, and a group of monitoring periods is executed, the monitoring period is the pre-set period, which is generally 1 min, which is determined in advance by the operator according to experience, and the other contact points of different monomer steel pieces are recorded as to-be-identified points. In the monitoring period, it is confirmed whether the other to-be-identified points have abnormal stress data, if yes, the corresponding to-be-identified points are recorded as abnormal contact points synchronously, if not, no marking is needed, and if all to-be-identified points do not have abnormal stress data, an error signal is directly generated for display (may be caused by damage of strain gauge, human intervention is needed for detection); The monomer steel piece with all surrounding contact points being abnormal contact points is recorded as an abnormal steel piece, and the confirmed abnormal steel piece is transmitted to the associated data analysis end, and then the stress data associated with the abnormal steel piece needs to be analyzed to identify the abnormal condition of the steel piece, which includes deviation 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 value change data generated by the strain gauge associated with different contact points of the abnormal steel piece, and confirms the change characteristics associated with different resistance value change data, and the multiple change characteristics are comprehensively checked, and a check signal is generated according to the check result for display; Wherein, the specific way of confirming the change characteristics is: Taking the current time as the initial time, a group of tracing periods is confirmed, and the tracing period is a preset period, generally 3 min, that is, in the past 3 min, the resistance value change data generated by the strain gauges associated with different contact points of the abnormal steel piece in the tracing period is confirmed, and a resistance value change curve associated with the strain gauge is directly generated, the horizontal coordinate axis of the curve is the time line, and the vertical coordinate axis is the resistance value; In different resistance value change curves associated with different strain gauges, the change characteristics of adjacent point positions are confirmed, the resistance value data of the next point position of the adjacent point position is Z1, the resistance value data of the previous point position is Z2, the change characteristics=(Z1-Z2), and the change characteristics of the adjacent point positions associated with different resistance value change curves are confirmed in turn; Wherein, the specific way of comprehensive checking of multiple change characteristics is: From different resistance value change curves associated with different strain gauges, the curve point position with the maximum difference of distance standard resistance value Zr is locked, and is marked in the corresponding resistance value change curve, and is recorded as a marked point, and Zr is a preset standard resistance value, that is, the resistance value of the monitored strain data is 0 state; The time associated with different marked points is recorded as a marked time, the time period associated between multiple marked time periods is recorded as a to-be-processed time period, the marked points associated with different resistance value change curves are moved forward and backward in the to-be-processed time period, and the moving process is recorded, the same trend at the same period is confirmed: the marked points are randomly moved to the specified position of the to-be-processed time period, the multiple partial curve segments associated in the to-be-processed time period are checked, and whether the change characteristics between adjacent point positions are positive or negative is identified, if yes, the time period between the corresponding adjacent point positions is recorded as a same trend time period, otherwise, it is recorded as a different trend time period, and the lengths of the same trend time period or the different trend time period are compared: If the same trend time period is longer, the current moving process is recorded as a same trend process, and the length of the same trend time period confirmed is recorded as the process characteristic of the same trend process; If the different trend time period is crossed, the current moving process is recorded as a different trend process, and the length of the different trend time period confirmed is recorded as the process characteristic of the different trend process; The same trend process or the different trend process of a plurality of moving processes is divided, the process characteristics of the same trend process are summed up and recorded as a same trend total value, and the process characteristics of the different trend process are summed up and recorded as a different trend total value; If the same trend total value is greater than the different trend total value, a steel piece deformation signal is generated (when deformed, the two strain gauges move relative to each other, that is, they move towards the middle at the same time, and in this case, the resistance value change trends of the two strain gauges are the same, which belongs to the deformation process); If the same trend sum value < the different trend sum value, a steel piece dislocation signal is generated (when dislocated, both sides change synchronously, and the resistance value change process is relatively consistent); If the same trend sum value = the different trend sum value, an error signal is directly generated (this kind of situation almost does not occur, but if it occurs, it needs to be detected artificially).

[0015] Part of the data in the above formula is dimensionless numerical calculation, and the contents not described in detail in the specification all belong to the prior art known to those skilled in the art.

[0016] The above examples are only used to illustrate the technical method of the present application and are not limited. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

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 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 a verification signal based on the verification results for display.

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: 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 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, The specific method by which the associated data analysis terminal confirms the change characteristics 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.

6. The intelligent monitoring system for steel structure deformation according to claim 5, characterized in that, The specific method by which the associated data analysis terminal comprehensively verifies 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 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.

7. The intelligent monitoring system for steel structure deformation according to claim 6, 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.

8. The intelligent monitoring system for steel structure deformation according to claim 6, 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