Large building structure safety monitoring parameter configuration method and system and monitoring method and system

Abstract

The invention discloses a large building structure safety monitoring parameter configuration method and system, and a monitoring method and system. The method comprises the steps of collecting and preprocessing historical data of monitoring items; dividing the preprocessed historical data into a plurality of time windows, and obtaining the maximum change rate and the maximum change trend of the historical data; collecting real-time monitoring data of the monitoring item, performing comparative analysis on the change rate of the real-time monitoring data and the maximum change rate of the historical data, and judging whether the parameter configuration value of the monitoring item is abnormal or not based on a comparative analysis result; obtaining parameter configuration information needing to be adjusted based on the anomaly judgment result and the maximum change trend of the historical data; and updating the parameter configuration of the monitoring item. According to the method, data trend change judgment, dynamic identification of parameter configuration and automatic and intelligent parameter configuration are realized based on big data, and the problems that abnormal parameter configuration depends on manpower and the adaptability is poor in the existing automatic monitoring technology can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic monitoring, in particular to a large building structure safety monitoring parameter configuration method and system, and a monitoring method and system. BACKGROUND

[0002] In the existing field of automatic monitoring of large building structure safety, the industry has certain limitations in monitoring key monitoring items such as strain, surface displacement, internal displacement, inclination, deflection, and abnormal parameter configuration.

[0003] In the aspect of abnormal parameter configuration identification, the industry often relies on artificial experience to set fixed judgment rules. For example, in a certain bridge monitoring project, technical personnel determine the normal range of monitoring item data through artificial judgment based on experience from similar past projects, and when the monitored strain data exceeds the range, it is determined to be abnormal. However, the actual monitoring environment is complex and variable, and factors such as temperature changes in different seasons and traffic flow differences can change the normal strain range of the bridge structure. Fixed judgment rules cannot adapt to these changes in a timely manner, and are prone to misjudgment or omission.

[0004] In addition, in the parameter configuration update link, current methods mostly rely on manual operation. For example, in a large building structure safety monitoring project, when data analysts find that the displacement data is abnormally fluctuating, they need to manually log in to the monitoring platform, find the monitoring parameters of the corresponding monitoring item among numerous parameter setting options, and then modify the parameter values according to their own experience to adjust the abnormal parameter configuration (spur threshold, sliding mean window, sliding median window, derivative threshold, number of gradual change points, gradual change threshold, etc.) of the monitoring item. This method is extremely inefficient, and when faced with a large number of parameters and frequent data changes, manual operation is prone to errors, seriously affecting the real-time and accuracy of the monitoring system.

[0005] In summary, the existing large building structure safety monitoring parameter configuration method or monitoring method has the following problems or shortcomings: 1. Poor adaptability: fixed judgment rules set by artificial experience cannot adapt to complex and variable actual monitoring environments. For example, in bridge monitoring, factors such as seasonal temperature changes and traffic flow differences can dynamically change the normal strain range of the bridge structure, but fixed rules cannot respond to these changes in real time, leading to misjudgment of normal fluctuations as abnormal or omission of real abnormal data in cases such as thermal expansion and contraction of the bridge caused by sudden temperature changes, sudden increase in traffic load, etc., resulting in misjudgment or omission, and reducing the reliability of monitoring results.

[0006] 2. Low efficiency: The manual parameter configuration update method is tedious and time-consuming when facing a large number of monitoring parameters and frequent data changes. For example, in a large building structure safety monitoring project, when there is abnormal fluctuation in displacement data, the data analyst needs to manually log in to the monitoring platform and find the corresponding parameters from numerous parameter options to modify them. In a large-scale monitoring scenario, this operation cannot meet the real-time monitoring needs, leading to delayed abnormal handling and inability to respond to potential risks in a timely manner.

[0007] 3. Error-prone: Manual operation is greatly affected by subjective factors and fatigue, and errors may occur during complex parameter configuration updates, such as incorrect parameter selection and incorrect numerical input. Once an error occurs, it not only fails to effectively solve the monitoring data anomaly problem, but also may cause new false positives or false negatives, disrupting normal monitoring work, and even causing the monitoring system to fail due to incorrect parameter configuration, seriously misleading the safety assessment of the monitored object.

[0008] 4. Lack of self-optimization capability: The existing method relies entirely on manual intervention, and the system itself does not have the ability to automatically optimize abnormal parameter configuration based on monitoring data characteristics and environmental changes. It cannot actively learn historical data patterns or adjust judgment rules and parameter configurations in new monitoring scenarios or data patterns, making it difficult to meet the growing intelligent and precise needs of the automated monitoring field. SUMMARY

[0009] The present application aims to address the shortcomings of the prior art by providing a large building structure safety monitoring parameter configuration method and system, as well as a monitoring method and system, to at least solve one of the problems of the prior art.

[0010] To solve the above technical problems, the technical solution adopted by the present application is as follows: A large building structure safety monitoring parameter configuration method, characterized by the following steps: Step 1, collect and preprocess structure safety monitoring historical data; Step 2, divide the preprocessed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtain the maximum change rate and maximum change trend of the historical data; Step 3, collect real-time monitoring data of the monitoring item, divide the real-time monitoring data into time windows, and obtain the change rate and change trend information of the real-time monitoring data in the time windows; compare and analyze the change rate of the real-time monitoring data and the maximum change rate of the historical data, and based on the comparison and analysis result, judge whether the parameter configuration value of the monitoring item is abnormal; based on the abnormal judgment result and the maximum change trend of the historical data, obtain the parameter configuration information that needs to be adjusted; Step 4, based on the adjusted parameter configuration information obtained in step 3, updating the parameter configuration of the monitoring item according to a preset rule, wherein the preset rule is: If there is no exception, obtaining the adjusted parameter configuration information based on the maximum change trend of the historical data, the configured parameters including the spike threshold, the sliding mean window and the sliding median window, the derivative threshold, the number of gradual change points and the gradual change threshold; If there is an exception, analyzing the correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item, and optimizing the adjusted parameter configuration information based on the correlation analysis result. As a preferred mode, the adjusted parameter configuration information includes: The spike threshold, taking n times of the standard deviation of the historical data as the new spike threshold, wherein n is any positive number; the sliding mean window and the sliding median window, taking a% of the number of granularity windows corresponding to the change range of the historical maximum change trend, wherein a is any positive number; The derivative threshold, adjusting according to the slope k, if the change speed of the slope k exceeds the preset value, then reducing the derivative threshold; The number of gradual change points, configuring the number of gradual change points as the number of granularity windows corresponding to the change range of the historical maximum change trend of normal data; The gradual change threshold, configuring the gradual change threshold as the first-end difference value corresponding to the change range of the historical maximum change trend of normal data.

[0011] As a preferred mode, the analysis of the correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item, and the adjusted parameter configuration information based on the correlation analysis result includes: Analyzing the correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item; Setting a fitness function F based on the correlation analysis result, the false positive situation of normal data and the false negative situation of abnormal data; Optimizing the fitness function F, and taking the parameter configuration information corresponding to the minimum value of F as the adjusted parameter configuration information.

[0012] As a preferred mode, the change rate of the historical data in the time window or the change rate of the real-time monitoring data is obtained by the following method: Obtaining the change trend curve of the data in the time window by fitting; Calculating the change rate m according to the change trend curve, wherein , is the maximum change amount of the data in the time window, is the length of the time window; Wherein, the data in the time window corresponds to the historical data or the real-time monitoring data. As a preferred mode, in step 2, the maximum change trend of the historical data includes: Step 201, continuously slide the time window backward from the first historical data, make linear fitting on the historical data in each time window, and obtain the slope k of the fitting straight line of the historical data in each time window; Step 202, according to the positive and negative values of the slope k corresponding to the first time window, the difference relationship between the slope k values corresponding to the first time window and the subsequent time windows, judge the maximum change trend of the historical data.

[0013] As a preferred mode, the step 202 comprises: whether the compliance rate meets the requirement, if yes, continue to slide the time window backward and judge whether the compliance rate meets the requirement, otherwise, take the time period between the first historical data and the historical data at which the slope changes in the opposite direction as a change trend window, and update the historical data at which the slope changes in the opposite direction as the first historical data, and jump to step 201; wherein the slope changes in the opposite direction means that the slope change trend changes from continuous increase to decrease, or the slope change trend changes from continuous decrease to increase; When step 201 traverses all historical data, compare the maximum value of all change trend windows as the maximum change trend Z of the historical data max ; The method for judging whether the compliance rate meets the requirement comprises: take the N groups of monitoring item values corresponding to the continuous change of the slope in the opposite direction, respectively calculate N groups of difference values between the N groups of monitoring item values and the last group of monitoring item values before the change of the slope in the opposite direction; When k>0, the proportion of the difference values greater than 0 in the total difference values reaches the target proportion, then the compliance rate meets the requirement, otherwise, it does not meet the requirement; When k<0, the proportion of the difference values less than 0 in the total difference values reaches the target proportion, then the compliance rate meets the requirement, otherwise, it does not meet the requirement.

[0014] As a preferred mode, in step 3, the change rate of the real-time monitoring data and the maximum change rate of the historical data are compared and analyzed, and based on the comparison and analysis result, whether the parameter configuration value of the monitoring item is abnormal is judged, comprising: if the continuous L1 change rates of the real-time monitoring data all exceed A times of the maximum change rate of the historical data, it is judged that the parameter configuration value of the monitoring item is abnormal; otherwise, the parameter configuration value of the monitoring item is not abnormal; wherein L1 and A are both preset values.

[0015] Based on the same inventive concept, the application also provides a parameter configuration system, which is characterized by comprising: a data acquisition module: used for acquiring historical data of monitoring items and real-time monitoring data of monitoring items; Data preprocessing module: used to preprocess historical data of monitoring items; Data analysis module: It is used to divide the pre-processed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtain the maximum change rate and maximum change trend of the historical data; Used to divide real-time monitoring data into time windows and obtain the change rate and change trend information of the real-time monitoring data within the time window; compare and analyze the change rate of the real-time monitoring data and the maximum change rate of the historical data, and based on the comparative analysis results, determine whether there is an abnormality in the parameter configuration value of the monitoring item; based on the abnormality judgment result and the maximum change trend of the historical data, obtain the parameter configuration information that needs to be adjusted; Parameter configuration adjustment module: used to update the parameter configuration of the monitoring item based on the obtained parameter configuration information that needs to be adjusted.

[0016] Based on the same inventive concept, the present invention also provides a monitoring method, which is characterized in that the monitoring method includes using the large-scale building structure safety monitoring parameter configuration method to update the parameter configuration of the monitoring items.

[0017] Based on the same inventive concept, the present invention also provides a monitoring system, characterized in that the monitoring system includes the parameter configuration system, which is used to update the parameter configuration of the monitoring items of the monitoring system. Compared with the existing technology, the present invention has significant advantages in many aspects: 1. Improved monitoring accuracy: Traditional technologies rely on simple filtering and manual judgment, which are difficult to handle in complex data and changing environments, and are prone to misjudgments or omissions. The present invention incorporates a data preprocessing module to preprocess data (e.g., deburring through adaptive filtering combined with wavelet transforms), which can more accurately remove data noise and ensure data quality. Furthermore, an anomaly detection method based on the maximum change rate and maximum change trend of historical data can dynamically adjust the judgment criteria based on the actual operating status of the monitored item, significantly improving the accuracy of anomaly identification.

[0018] 2. Enhanced system adaptability: Existing technologies rely on manual experience to set fixed rules and are unable to adapt to changes in the monitoring environment. This invention, through in-depth analysis of historical big data, automatically learns the changing patterns and trend characteristics of monitoring data. When the monitoring scene changes due to factors such as seasonal changes, changes in traffic flow, and progress in construction, the invention can automatically adjust abnormal parameter configurations (such as glitch thresholds, sliding window size, derivative thresholds, etc.), ensuring that the monitoring system always maintains optimal working conditions, greatly enhancing its adaptability to different working conditions and environments.

[0019] 3. Improve work efficiency: In the traditional monitoring method, parameter configuration update depends on manual operation, the process is complicated and time-consuming. The present application realizes the automatic operation from data acquisition, processing, abnormality identification to parameter configuration update. Once the data anomaly is monitored, the parameter configuration can be quickly and automatically analyzed and optimized, and the new parameter configuration information is sent to the monitoring platform for update in real time, meeting the efficiency requirement of real-time monitoring, especially suitable for large-scale monitoring projects with large data volume and frequent changes.

[0020] 4. Reduce the risk of human error: Manual operation is easily affected by subjective factors and fatigue state, and errors are easily made in the complex parameter configuration process. The present application completely abandons manual intervention and automatically executes parameter configuration optimization through algorithm and program, avoiding manual errors such as wrong parameter selection and value input, ensuring the accuracy and consistency of parameter configuration, effectively reducing the monitoring errors caused by human errors, and improving the stability and reliability of the monitoring system.

[0021] 5. Intelligent self-optimization: The existing technology lacks self-optimization ability and cannot actively adapt to new monitoring scenarios and data patterns. The present application has self-learning and optimization ability based on big data analysis and optimization algorithm, can continuously improve the abnormality judgment and parameter configuration information with the accumulation of monitoring data, and continuously improves the performance of the monitoring system, providing important technical support for the intelligent development of automatic monitoring field. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 Flowchart for an embodiment of the large building structure safety monitoring parameter configuration method of the present application.

[0023] Figure 2 Block diagram of an embodiment of the parameter configuration system of the present application. Wherein, 1 is a data acquisition module, 2 is a data preprocessing module, 3 is a data analysis module, and 4 is a parameter configuration adjustment module.

[0024] Figure 3 Bridge strain monitoring item historical data schematic diagram, showing the maximum change rate of historical data identified by the present application.

[0025] Figure 4 Bridge strain monitoring item historical data schematic diagram, showing the maximum change trend of historical data identified by the present application.

[0026] Figure 5 Bridge strain monitoring item data identification before and after parameter configuration update using the present application, showing the data before update processing.

[0027] Figure 6For the data recognition situation of the bridge strain monitoring item before and after the parameter configuration update using the present application, the data situation after the update processing is shown in the figure.

[0028] Figure 7 For the data recognition situation of the bridge strain monitoring item before and after the parameter configuration update using the present application, the data situation after the update processing is shown in the figure. DETAILED DESCRIPTION

[0029] In order to enable personnel in the art to better understand the present application scheme, the technical solutions in the embodiments of the present application are described clearly and completely below in combination with the accompanying drawings in the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should belong to the scope of protection of the present application.

[0030] The present application is dedicated to solving the technical problems of excessive dependence on manual experience, poor adaptability, low efficiency and easy to make mistakes of abnormal parameter configuration in the existing automatic monitoring field. In the traditional way, the fixed judgment rule is difficult to adapt to the complex and changeable monitoring environment, and the manual updating of parameter configuration is not only low in efficiency, but also easy to make mistakes, and the system lacks self-optimization ability, which cannot meet the increasing intelligent demand of automatic monitoring.

[0031] The present application realizes data trend change judgment, dynamic identification of parameter configuration and automatic intelligent implementation of parameter configuration based on big data, aiming to solve the problems of dependence on manual work and poor adaptability of abnormal parameter configuration in the existing automatic monitoring technology.

[0032] As shown in Figure 1 and Figure 2 The first aspect of the embodiment of the present application provides a large building structure safety monitoring parameter configuration method and a corresponding parameter configuration system.

[0033] The large building structure safety monitoring parameter configuration method of the present application includes the following steps: Step 1, collecting and preprocessing the historical data of the structure safety monitoring item.

[0034] Data collection: Various sensors in the monitoring system, including strain sensors, displacement sensors, inclination sensors, etc., collect monitoring data such as strain, surface displacement, internal displacement, inclination and deflection in real time. The sensors transmit data to the data acquisition module 1 through wired or wireless communication.

[0035] Data preprocessing: According to the system data verification rules, the data is strictly checked, and the inspection content includes the integrity of the data and the validity of the data. Checking the integrity of the data means confirming that there are no missing values ​​in the data; checking the validity of the data means judging whether the data value is within a reasonable range, for example, the strain value cannot exceed the range of the corresponding sensor. Once invalid data is found, it is immediately eliminated. Subsequently, the data is deburred, which is a key link to ensure data quality. Deburring is preferably, but not limited to, using an adaptive filtering method, which dynamically adjusts the data filtering range according to the changing characteristics of the data itself to remove interference from other factors in the data. In a preferred embodiment, deburring the data includes: all data in the collected data group Perform data difference calculation, where For the first data, The value range of is 1 to n. The data difference calculation method is to calculate the difference between the next granularity data and the previous granularity data. data points , calculate its difference with the previous data point The difference between , we can get the data set with data difference 、 If the difference between two consecutive data All in In addition ( is the average value of the data difference group, is the standard deviation of the data difference group), the corresponding data is determined to be abnormal burr data, and the cleaned data is obtained after filtering through the optimization algorithm, and the burr threshold is recorded at the same time. Step 2: Divide the pre-processed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtain the maximum change rate and maximum change trend of the historical data.

[0036] Step 2 preferably includes but is not limited to: Time window division: Collect preprocessed historical data (e.g., the previous year's preprocessed data) and divide it into multiple time windows (for example, 365 time windows per day) in chronological order, based on predefined time periods (which can be arbitrarily divided into minutes, hours, or days). Each time window contains a certain number of data points. During actual monitoring, the time window size can be flexibly adjusted based on actual monitoring needs.

[0037] Polynomial fitting: For the data in each time window, a polynomial fitting method is used to construct a data trend curve. The polynomial fitting process preferably includes, but is not limited to: for the data in each time window, multiple polynomial fittings are performed using the least squares method. Taking the third-order polynomial fitting as an example, assuming that the number of data points in the time window is 200, assuming The data point value corresponding to the moment is , the fitting polynomial is ,in, For the moment The corresponding fitted value. By minimizing the error function ( for Corresponding fitting values), calculate the polynomial coefficients a0, a1, a2, a3, and obtain the data change trend curve. Change rate calculation: The rate of change m of the data in each time window is calculated based on the trend curve. The rate of change reflects the speed of change of the data in the time period. is the maximum change of data in the time window, is the length of the time window. Compare the change rates of all time windows and find the maximum value, which is the maximum change rate of the data. Identification of the biggest change trend in historical data: The increase or decrease of data is determined by the slope k of the change curve, thereby determining the maximum change trend of historical data. This trend will serve as an important reference for subsequent abnormal parameter configuration.

[0038] The identification of the largest change trend of historical data preferably includes but is not limited to: Step 201: Take historical pre-processed data (such as the historical pre-processed data of the previous year), continuously slide the time window backward from the first historical data, and perform linear fitting on the historical data in each time window. ,in, Historical data in each time window The corresponding linear fitting value is is the slope of the fitting line of historical data in each time window, The intercept of the fitted line for the historical data within each time window. Step 202: Determine the maximum trend of change in the historical data based on the sign of the slope k corresponding to the first time window (k < 0, the function is decreasing; k > 0, the function is increasing) and the difference between the slope k values ​​for the first time window and subsequent time windows. If the slope continuously shifts in one direction, but the slope changes in the opposite direction for N consecutive time windows, and the first slope changes in the opposite direction, compare the sign of the slope k.

[0039] The step 202 preferably but not limited to comprises: judging whether the compliance rate meets the requirement, if yes, continuing to slide the time window backward and judging whether the compliance rate meets the requirement; otherwise, taking the time period between the first historical data and the historical data at which the slope changes in the opposite direction as a change trend window, and updating the historical data at which the slope changes in the opposite direction to the first historical data, and jumping to step 201; wherein the slope changes in the opposite direction refers to that the slope change trend changes from continuous increase to decrease, or the slope change trend changes from continuous decrease to increase; When step 201 traverses all historical data, the maximum value of all change trend windows is compared to obtain the maximum change trend Z of the historical data max ; wherein the method for judging whether the compliance rate meets the requirement comprises: Taking the N groups of monitoring item values corresponding to the time when the slope changes in the opposite direction, N groups of difference values between the N groups of monitoring item values and the last group of monitoring item values before the slope changes in the opposite direction are calculated respectively; When k>0, if the proportion of the difference values greater than 0 in the total difference values reaches the target proportion, the compliance rate meets the requirement, otherwise, the compliance rate does not meet the requirement; When k<0, if the proportion of the difference values less than 0 in the total difference values reaches the target proportion, the compliance rate meets the requirement, otherwise, the compliance rate does not meet the requirement. The following takes strain monitoring as an example to illustrate how to obtain the maximum change trend of historical data in a specific application case: the slope k continuously changes in a single direction in the previous time window, when k changes in the opposite direction for five groups in succession, for example, the current fitting slope k=0.678 (k increases in the direction), and the slope decreases for five particle sizes (the particle size window can be adjusted) in succession, for example, 0.665, 0.659, 0.643, 0.631, 0.622) (k continuously decreases). If the slope k>0 / k<0, then the strain value corresponding to the particle size when the slope changes in the opposite direction-the strain value corresponding to the last group of particle size changes in the same direction of the slope>0 / <0 (5 groups of data reach 60%, wherein the group number, i.e. the target proportion, can be adjusted according to actual requirements), then the change trend identification is continued; if the compliance rate does not meet the requirement, then the first data to the first time window at which the slope changes in the opposite direction is taken as a change trend window ; the next change trend window starts from the first time window at which the slope changes in the opposite direction, and so on to obtain ,... ; the maximum change trend of the historical data is found , which automatically selects the corresponding time window number (data corresponding to the particle size number) and data range. Specifically, the processing process and effect of the present application on bridge strain monitoring items are illustrated as shown in Figures 3-4 , and Figure 3The figure shows the maximum change rate of historical data identified by the application , Figure 4 The figure shows the maximum change trend of historical data identified by the application .

[0040] Step 3, collect real-time monitoring data of the monitoring item, divide the real-time monitoring data into time windows, and obtain the change rate and change trend information of the real-time monitoring data in the time windows; compare and analyze the change rate of the real-time monitoring data and the maximum change rate of the historical data, judge whether the parameter configuration value of the monitoring item is abnormal based on the comparison and analysis result; and obtain the parameter configuration information to be adjusted based on the abnormality judgment result and the maximum change trend of the historical data.

[0041] In step 3, the parameter configuration information to be adjusted is obtained based on the abnormality judgment result and the maximum change trend of the historical data, which preferably but not limited to includes: If there is no abnormality, the parameter configuration information to be adjusted is obtained based on the maximum change trend of the historical data; If there is an abnormality, the correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item is analyzed and obtained, and the parameter configuration information to be adjusted is obtained based on the correlation analysis result.

[0042] The correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item is analyzed and obtained based on the correlation analysis result, and the parameter configuration information to be adjusted is obtained, which preferably but not limited to includes: The correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item is analyzed and obtained; Set the fitness function F based on the correlation analysis result, the normal data misjudgment situation and the abnormal data missed judgment situation; Optimize the fitness function F, and take the parameter configuration information corresponding to the minimum value of F as the parameter configuration information to be adjusted.

[0043] In step 3, the change rate of the real-time monitoring data and the maximum change rate of the historical data are compared and analyzed, and whether the parameter configuration value of the monitoring item is abnormal is judged based on the comparison and analysis result, which preferably but not limited to includes: if the continuous L1 change rates of the real-time monitoring data all exceed A times of the maximum change rate of the historical data, it is judged that the parameter configuration value of the monitoring item is abnormal; otherwise, the parameter configuration value of the monitoring item is not abnormal; wherein L1 and A are both preset values.

[0044] Step 3 is to identify abnormal parameter configurations. Based on the parameter change characteristics presented by the maximum change trend of historical data, such as the range and speed of strain change under the maximum change trend, combined with preset adjustment rules, the abnormal parameter configuration items that need to be adjusted are determined, including burr threshold, sliding mean window, sliding median window, derivative threshold, number of gradient points, gradient threshold, etc. Then, these parameters are adjusted and optimized through a specific optimization algorithm to obtain the parameter configuration solution that best suits the current monitoring situation. In a specific application case, step 3 includes: Real-time data processing: For real-time monitoring data, the same method of processing historical data is used to divide it into time windows, and polynomial fitting and change rate calculation are performed. Abnormal judgment: When the change rate of real-time data exceeds the maximum change rate of historical data, A times (the multiple A is adjustable, such as A is 1.2), and the change trend continues for L1 time windows (the number of time windows L1 is adjustable, such as L1 is 5), then the current data is determined to be abnormal. Parameter configuration adjustment (when there is no abnormality in the current data): According to the parameter change characteristics involved in the maximum change trend of historical data (such as the range of strain change under the maximum change trend to determine the corresponding number of gradient points and gradient threshold), combined with preset rules (such as the faster the change speed, the smaller the derivative threshold; the larger the change range, the larger the gradient threshold), determine the abnormal parameter configuration items that need to be adjusted (burr threshold 3σ, sliding mean window, sliding median window, derivative threshold, number of gradient points, gradient threshold, etc.) and the adjustment direction. Specific adjustment rules can be: 1) Burr threshold Rule: 3 times the standard deviation of historical data is used as the glitch threshold.

[0045] Setting method: Glitch threshold = 3σ 3σ means that 99.7% of normal data will fall within this range. Any sudden, transient mutation point exceeding this threshold will be identified as a "glitch" anomaly, meaning it captures a point anomaly.

[0046] 2 / 3) Sliding mean window and sliding median window Rule: The range of the historical maximum change trend corresponds to 5% (or other proportional value) of the granularity windows.

[0047] Setting method: Sliding window size = N_zmax * α (where α is the proportional coefficient, such as 5%, i.e. 0.05) N_zmax represents the time span required for the system to complete a "maximum normal change." The window size must be much smaller than this time span (e.g., 5%) to ensure: Sensitivity: The window is small enough to detect the beginning of a trend change.

[0048] Anti-noise: The window cannot be too small (otherwise it is the original data), which can effectively smooth out the tiny and meaningless fluctuations.

[0049] This window is used to filter random noise, providing a smoother data basis for calculating derivatives and trends.

[0050] 4) Derivative threshold Rule: Adjust according to the slope k (the faster the change speed, the smaller the derivative threshold).

[0051] Setting method: Derivative threshold = ω / |k_zmax| (ω is an empirical coefficient, in order to reduce false positives, ω is generally between 1.2 and 1.8, which can be adjusted according to actual situation) k_zmax is the maximum historical change trend The fastest change speed. The faster the change speed, the lower the derivative threshold should be set (more sensitive). Because if the normal change is very fast, then a change slightly slower than k_zmax may be normal; but if a change speed close to or even exceeds the historical maximum speed k_zmax, it is very suspicious and needs to be detected. Lowering the threshold can improve the detection sensitivity of abnormal high-speed changes.

[0052] 5) Number of trend points Rule: The number of granularity windows corresponding to the change range of the maximum historical change trend of normal data.

[0053] Setting method: Number of trend points = N_zmax This configuration rule aims to detect "persistent anomalies". An abnormal trend process needs to last at least N_zmax to "disguise" as normal change, in order to have an impact comparable to the maximum historical normal change (Δ_zmax). Therefore, setting the detection window directly to N_zmax means that the system will continuously monitor a period of N_zmax, and if the cumulative change of the data exceeds the expected value based on historical learning (Δ_zmax) during this entire period, it will be reported as an anomaly.

[0054] 6) Trend threshold Rule: The first and last difference corresponding to the change range of the maximum historical change trend of normal data.

[0055] Setting method: Trend threshold = Δ_zmax This is used in conjunction with the previous configuration rule, which defines the maximum cumulative change allowed within N_zmax time windows. Any trend with a change amplitude exceeding Δ_zmax within the same or shorter time will be judged as an abnormal trend.Figure 5 In order to identify the data of bridge strain monitoring items before and after parameter configuration update using the present invention, the data before update processing is shown. Figure 6 The data after the update is shown in the figure. Figure 7 FIG. 3 shows abnormal data identified by using the present invention.

[0056] Parameter configuration optimization and adjustment (when current data contains anomalies): After discovering data anomalies, correlation analysis is performed. Through the direct correlation between parameters and anomaly results, the impact of individual parameters on anomaly identification is focused on. Quantitative analysis is used to clarify the correlation between "parameter adjustment" and "number of false positives / missed positives." For example, the Pearson correlation coefficient is used to calculate the correlation strength between the adjustment amount of the derivative threshold and the number of missed anomalies. If the absolute value of the correlation coefficient is ≥0.7, it indicates a strong correlation between the two, indicating that the derivative threshold is the core parameter affecting missed positives and the missed positive weight index is high. If not, the correlation is continued with other parameters.

[0057] Use genetic algorithms to optimize parameters and set fitness functions , where the number of normal data misjudgments and the number of abnormal data omissions are determined by manual review and identification. 、 is the weight coefficient, and the weight is adjusted according to the correlation. If the absolute value of the correlation coefficient between the parameter and the number of missed judgments is ≥ 0.7, it can be set to the corresponding parameter. , the specific meaning is that it pays more attention to the number of missed judgments). Through genetic operations such as selection, crossover, and mutation, it is continuously iterated and optimized, and the size of F is compared (selecting the high-quality combination with the smallest F) to obtain the optimal parameter configuration.

[0058] Specifically, 1) Phase 1: Correlation Analysis (Diagnosis Phase) Objective: To identify the key parameters that lead to “false positives / missed positives” and set priorities for subsequent optimization.

[0059] Specific steps: Collect data: Run the system under the current parameter configuration, record the anomaly recognition results over a period of time, and compare them with the actual results from manual review. Record the number of "false positives" and "missed positives" at each time point.

[0060] Perturb parameters: Systematically and subtly adjust each parameter to be optimized (e.g., increase or decrease the derivative threshold by 5%, increase or decrease the window size by 10 granularity, etc.). Change only one parameter at a time, keeping the others constant, and record the number of false positives and false negatives after each adjustment.

[0061] Quantitative correlation: For each parameter (e.g. derivative threshold), calculate the Pearson correlation coefficient between its adjustment amount (proportion of change relative to the original value) and the change in the number of false negatives / misses.

[0062] Pearson correlation coefficient: Measures the degree of linear correlation between two variables, with a value range of [-1, 1].

[0063] As a preferred embodiment of the invention, but not representing that the invention can only be set in this way, such as setting when the absolute value ≥ 0.7: strong correlation.

[0064] Absolute value around 0.5: moderate correlation.

[0065] Absolute value ≤ 0.3: weak correlation.

[0066] Diagnosis conclusion: If the correlation coefficient between the adjustment amount of the derivative threshold and the change in the number of misses is greater than or equal to 0.7 (strong negative correlation), it means that lowering the derivative threshold will significantly reduce the number of misses. Conversely, it also means that. This confirms that the derivative threshold is the core parameter causing the miss problem and needs to be optimized.

[0067] 2) Second stage: Genetic algorithm optimization (solution stage) Objective: Based on the diagnosis results of the first stage, automatically find the optimal parameter configuration Individual: A specific set of parameters. For example: Individual 1 = {spike threshold: 3.1σ, sliding window: 15, derivative threshold: 0.08,...} Population: A collection of different parameter configurations.

[0068] Fitness function: This is the core of the genetic algorithm, used to evaluate the goodness of a set of parameters. The smaller the function value F, the better the set of parameters.

[0069] F =

[0070] Key point: Weight coefficient And It is not fixed, but is dynamically set according to the correlation analysis results of the first stage.

[0071] If it is found that the derivative threshold is strongly correlated with the number of misses (|r| ≥ 0.7), then when optimizing, we should give a higher weight to the number of misses (i.e. increase ), so that the algorithm can find solutions that reduce misses first.

[0072] Similarly, if the spike threshold is strongly correlated with the number of false positives, increase .

[0073] In this way, the fitness function F becomes a focused, targeted optimization goal.

[0074] Genetic operations: Selection: Select good individuals with small F (high fitness) from the current population, and let them have a higher probability of "reproducing" the next generation.

[0075] Crossover: Mimic gene recombination. For example, combine the parameters of two excellent parent individuals (such as the parent's window size and the mother's derivative threshold) into a new child individual.

[0076] Mutation: Randomly change a parameter value of an individual with a small probability (for example, fine-tune the number of gradient points of an individual from 50 to 52) to introduce diversity and avoid the algorithm falling into a local optimal solution.

[0077] Iteration: Repeat the process of "calculate fitness -> selection -> crossover -> mutation" to generate generation after generation. Each generation will tend to be more optimal.

[0078] Termination and output: When the maximum number of iterations is reached, or the F value of the optimal individual no longer improves significantly for several generations, the algorithm stops. Output the individual with the smallest F value in the current population, which is the optimal parameter configuration combination.

[0079] Step 4, based on the parameter configuration information obtained in step 3, update the parameter configuration of the monitoring item. In some preferred embodiments, specifically, send the optimized abnormal parameter configuration information to the monitoring platform, accurately store the new parameter configuration information in the database. At the same time, the monitoring platform will update the front-end display interface and data processing logic synchronously, so that the entire monitoring system runs based on the new parameter configuration scheme, realizes the automatic update of the parameter configuration, and more accurately monitors the monitoring object in real time.

[0080] As shown in Figure 2 The parameter configuration system provided by the present application corresponds to the inventive concept of the above-mentioned large building structure safety monitoring parameter configuration method, and the parameter configuration system preferably comprises but is not limited to: Data acquisition module 1: used for acquiring historical data of monitoring items and real-time monitoring data of monitoring items; Data preprocessing module 2: used for preprocessing historical data of monitoring items; Data analysis module 3: used for dividing the preprocessed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtaining the maximum change rate and maximum change trend of the historical data; The real-time monitoring data is divided into time windows, and the change rate and change trend information of the real-time monitoring data in the time windows are obtained; the change rate of the real-time monitoring data and the maximum change rate of the historical data are compared and analyzed, and based on the comparison and analysis result, it is judged whether the parameter configuration value of the monitoring item is abnormal; based on the abnormality judgment result and the maximum change trend of the historical data, the parameter configuration information to be adjusted is obtained; The parameter configuration adjustment module 4 is configured to update the parameter configuration of the monitoring item based on the obtained parameter configuration information to be adjusted.

[0081] The data acquisition module 1, the data preprocessing module 2, the data analysis module 3, and the parameter configuration adjustment module 4 are used to implement the large building structure safety monitoring parameter configuration method.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of the functional units and modules are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0083] The embodiment of the application further provides a monitoring method, which comprises updating the parameter configuration of the monitoring item by using the large building structure safety monitoring parameter configuration method.

[0084] The embodiment of the application further provides a monitoring system, which comprises the parameter configuration system described above, and the parameter configuration system is used to update the parameter configuration of the monitoring item of the monitoring system.

[0085] For the parameter configuration system, the monitoring method, and the monitoring system, the parts corresponding to the invention points of the large building structure safety monitoring parameter configuration method are not repeated here, but do not affect the understanding and implementation of the application by those skilled in the art.

[0086] The concept of the present application is based on big data technology, and an intelligent parameter configuration system is constructed. The system deeply mines and analyzes massive historical monitoring data, removes burrs in the data by using a data processing algorithm, guarantees data quality, accurately identifies abnormal patterns in the data by using a data recognition algorithm, automatically determines and adjusts abnormal parameter configurations (including burr threshold, sliding mean window, sliding median window, derivative threshold, number of gradual change points, and gradual change threshold) according to the maximum change trend of historical data, and realizes dynamic optimization and intelligent update of parameter configuration without manual intervention.

[0087] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in a certain embodiment can be referred to the related description of other embodiments.

[0088] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0089] In the embodiments provided by the present application, it should be understood that the disclosed method and system can be implemented in other ways. For example, the above-described method and system embodiments are merely illustrative. For example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0090] The units described as separate components can or can not be physically separated, i.e., they can be located in one place or distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0091] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0092] The integrated module / unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0093] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for configuring parameters for safety monitoring of large building structures, characterized in that: The following steps are involved: Step 1: Collect and pre-process historical data of structural safety monitoring items; Step 2: Divide the preprocessed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtain the maximum change rate and maximum change trend of the historical data; Step 3: Collecting real-time monitoring data of the monitoring item, dividing the real-time monitoring data into time windows, and obtaining the change rate and change trend information of the real-time monitoring data within the time windows; performing a comparative analysis on the change rate of the real-time monitoring data and the maximum change rate of the historical data, and judging whether the parameter configuration value of the monitoring item is abnormal based on the comparative analysis results; Based on the abnormal judgment results and the maximum change trend of historical data, obtain the parameter configuration information that needs to be adjusted; Step 4: Based on the parameter configuration information to be adjusted obtained in step 3, update the parameter configuration of the monitoring item according to the preset rules. The preset rules are: If no anomaly exists, the parameter configuration information that needs to be adjusted is updated based on the maximum change trend of the historical data. The parameter configuration information that needs to be adjusted includes the burr threshold, the sliding mean window and the sliding median window, the derivative threshold, the number of gradient points, and the gradient threshold; If there is an anomaly, the correlation between the parameters of the monitoring item and the abnormal monitoring result of the monitoring item is analyzed and obtained, and the parameter configuration information that needs to be adjusted is optimized based on the correlation analysis result.

2. The large-scale building structure safety monitoring parameter configuration method according to claim 1 is characterized in that: The step of updating the parameter configuration information to be adjusted based on the maximum change trend of historical data specifically includes: Glitch threshold, n times the standard deviation of historical data is used as the new glitch threshold, where n is any positive number; For the sliding mean window and the sliding median window, the range of change of the historical maximum change trend corresponds to a% of the number of granularity windows, where a is any positive number; The derivative threshold is adjusted according to the slope k. If the slope k changes faster than the preset value, the derivative threshold is reduced. The number of gradient points is configured as the number of granularity windows corresponding to the range of the maximum historical change trend of normal data; Gradual change threshold: Set the gradual change threshold to the difference between the beginning and the end of the range of change corresponding to the maximum historical change trend of normal data.

3. The large-scale building structure safety monitoring parameter configuration method according to claim 2, characterized in that: The analysis to obtain the correlation between each parameter of the monitoring item and the abnormal monitoring result of the monitoring item, and obtaining the parameter configuration information to be adjusted based on the correlation analysis result includes: Analyze and obtain the correlation between each parameter of the monitoring item and the abnormal monitoring results of the monitoring item; The fitness function F is set based on the correlation analysis results, the misjudgment of normal data, and the omission of abnormal data; The fitness function F is optimized, and the parameter configuration information corresponding to the minimum value of F is used as the parameter configuration information that needs to be adjusted.

4. The method for configuring parameters for safety monitoring of large building structures according to claim 2, characterized in that: The change rate of historical data or real-time monitoring data within a time window can be obtained by: Fitting to obtain the changing trend curve of the data within the time window; Calculate the change rate m according to the change trend curve, where , is the maximum change of data in the time window, is the length of the time window; The data within the time window corresponds to historical data or real-time monitoring data.

5. The large-scale building structure safety monitoring parameter configuration method according to claim 1 is characterized in that: In step 2, obtaining the maximum change trend of historical data includes: Step 201: Slide the time window backward continuously from the first historical data, perform linear fitting on the historical data in each time window, and obtain the slope k of the fitting line of the historical data in each time window; Step 202 : Determine the maximum change trend of the historical data based on the positive and negative values ​​of the slope k corresponding to the first time window and the difference between the slope k values ​​corresponding to the first time window and the subsequent time windows.

6. The large-scale building structure safety monitoring parameter configuration method according to claim 5, characterized in that: The step 202 includes: Determine whether the compliance rate meets the requirements. If so, continue sliding the time window backward and determine whether the compliance rate meets the requirements. Otherwise, take the time period between the first historical data and the historical data where the slope starts to change in the opposite direction as a change trend window, and update the historical data where the slope starts to change in the opposite direction as the first historical data, and jump to step 201. After all historical data are processed in step 201, the maximum value of all change trend windows is obtained by comparison and is taken as the maximum change trend Z of the historical data. max ; Among them, the methods for judging whether the compliance rate meets the requirements include: Take the N groups of monitoring item values ​​corresponding to when the slope continuously changes in the opposite direction, and calculate the N groups of differences between the N groups of monitoring item values ​​and the last group of monitoring item values ​​before the slope changes in the opposite direction; When k>0, if the proportion of the number of differences greater than 0 in the N groups of differences in the total number of differences reaches the target proportion, then the compliance rate meets the requirement, otherwise it does not meet the requirement; When k is less than 0, if the proportion of the number of differences less than 0 in the total number of differences in the N groups reaches the target proportion, the compliance rate meets the requirements; otherwise, it does not meet the requirements.

7. The method for configuring parameters for safety monitoring of large building structures according to any one of claims 2 to 6, characterized in that: In step 3, comparing and analyzing the change rate of the real-time monitoring data and the maximum change rate of the historical data, and judging whether the parameter configuration value of the monitoring item is abnormal based on the comparative analysis result includes: If the L1 consecutive change rates of the real-time monitoring data exceed A times the maximum change rate of the historical data, it is judged that there is an abnormality in the parameter configuration value of the monitoring item; otherwise, there is no abnormality in the parameter configuration value of the monitoring item; wherein L1 and A are both preset values.

8. A large-scale building structure safety monitoring parameter configuration system, characterized in that: include: Data collection module: used to collect historical data of monitoring items and real-time monitoring data of monitoring items; Data preprocessing module: used to preprocess historical data of monitoring items; Data analysis module: It is used to divide the pre-processed historical data into multiple time windows; based on the change rate and change trend of the historical data in each time window, obtain the maximum change rate and maximum change trend of the historical data; Used to divide real-time monitoring data into time windows and obtain the change rate and change trend information of the real-time monitoring data within the time window; compare and analyze the change rate of the real-time monitoring data and the maximum change rate of historical data, and based on the comparative analysis results, determine whether there is any abnormality in the parameter configuration value of the monitoring item; Based on the abnormal judgment results and the maximum change trend of historical data, obtain the parameter configuration information that needs to be adjusted; Parameter configuration adjustment module: used to update the parameter configuration of the monitoring item based on the obtained parameter configuration information that needs to be adjusted.

9. A method for monitoring the safety of large building structures, characterized in that: The monitoring method includes updating the parameter configuration of the monitoring items using the large-scale building structure safety monitoring parameter configuration method according to any one of claims 1 to 7.

10. A large-scale building structure safety monitoring system, characterized in that: The monitoring system includes the parameter configuration system according to claim 8, and the parameter configuration system is used to update the parameter configuration of the monitoring items of the monitoring system.

Images