Pedestrian floor tile operation and maintenance management method and system based on big data analysis

Abstract

The invention relates to a pedestrian floor tile operation and maintenance management method and system based on big data analysis. The pedestrian floor tile operation and maintenance management method comprises the following steps: dividing a sidewalk network into monitoring areas, deploying a plurality of vibration sensors in each monitoring area according to preset space distribution, and acquiring vibration data of floor tiles under daily load; performing periodic comprehensive analysis on the vibration data in each monitoring area, and calculating to obtain an area vibration activeness index and an area vibration dispersion index of the monitoring area; performing long-term trend monitoring on the regional vibration activeness index and the regional vibration dispersion index of each monitoring region, and judging whether the regional vibration activeness index presents a continuous descending trend or not and whether the regional vibration dispersion index presents a continuous descending trend or a trend tending to be consistent or not by adopting a dynamic time window analysis method; and when the continuous descending trend of the regional vibration activeness index and the continuous descending trend of the regional vibration dispersion index are identified at the same time or tend to be consistent, judging that a settlement risk exists in the monitoring region, and generating and sending settlement risk early warning information. According to the invention, early effective early warning of the potential pavement collapse risk is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of digital city construction, and in particular to a pedestrian floor tile operation and maintenance management method and system based on big data analysis. BACKGROUND

[0002] In order to improve the safety of pedestrian travel and the efficiency of floor tile maintenance, the existing pedestrian floor tile operation and maintenance management system generally adopts a framework of "local monitoring + individual analysis": that is, through the vibration sensor built in a single floor tile, pedestrian stepping vibration data is collected to judge problems such as floor tile loosening and unstable support, and at the same time, the surface image of the floor tile is shot by a high-definition camera on a patrol vehicle, and cracks, missing corners, wear and other explicit damage are identified by combining image recognition and historical data comparison. After these data are processed by a preset analysis program (which is generally trained based on historical single floor tile damage cases), a work order containing damage location, type and repair level is automatically generated, resources are accurately allocated to handle isolated damage events, thereby reducing the blindness of manual patrol and the identification and disposal effect of local and explicit damage (such as loosening and cracking) of single floor tiles.

[0003] In the related art, the operation and maintenance management system has a serious technical defect, which relies on individual data such as vibration and surface image of a single floor tile, can only identify "local problems", but cannot perceive "overall changes", and therefore cannot cope with systemic risks caused by underground hidden factors. For example, when underground pipelines leak and other hidden factors cause large-scale roadbed progressive hollowing, the regional floor tiles will sink slowly and uniformly as a whole. From the performance point of view, the relative positions of adjacent floor tiles do not change, the vibration response of a single floor tile also maintains a normal threshold, and there are no cracks or abnormal gaps on the surface. At this time, the operation and maintenance management system will continue to output the wrong judgment that "the state of this area is good", and the management department will not know about the potential collapse risk.

[0004] Such misjudgment will directly miss the best intervention opportunity. Once external incentives such as heavy rain (rainwater accelerates the loss of cushioning layer) are encountered, it is easy to trigger a chain-type road collapse (such as a small vehicle triggering a critical point), causing serious public safety accidents, which urgently needs to be improved. SUMMARY

[0005] The present application provides a pedestrian floor tile operation and maintenance management method and system based on big data analysis, to at least solve the technical problem that the existing technology lacks effective sensing and early warning capabilities when facing large-scale, progressive roadbed hollowing problems caused by underground hidden factors, and cannot timely discover and handle potential risks.

[0006] In a first aspect, the present application provides a pedestrian floor tile operation and maintenance management method based on big data analysis, the method comprising: The sidewalk network is divided into monitoring areas, and a plurality of vibration sensors are deployed in each monitoring area according to a predetermined spatial distribution to collect vibration data of floor tiles under daily load; The vibration data in each monitoring area are periodically analyzed to obtain a regional vibration activity index and a regional vibration dispersion index of the monitoring area; The regional vibration activity index and the regional vibration dispersion index of each monitoring area are long-term trend monitored, and a dynamic time window analysis method is used to determine whether the regional vibration activity index presents a continuous downward trend and whether the regional vibration dispersion index presents a continuous downward trend or a consistent trend; When the continuous downward trend of the regional vibration activity index and the continuous downward trend or consistent trend of the regional vibration dispersion index are identified at the same time, it is determined that the monitoring area has a settlement risk, and the settlement risk warning information is generated and sent.

[0007] Optionally, the long-term trend monitoring of the regional vibration activity index and the regional vibration dispersion index of each monitoring area, and the use of a dynamic time window analysis method to determine whether the regional vibration activity index presents a continuous downward trend and whether the regional vibration dispersion index presents a continuous downward trend or a consistent trend, comprises: Collecting daily load pattern data in the monitoring area; Correlation analysis of the daily load pattern data and the regional vibration activity index and the regional vibration dispersion index; When the regional vibration activity index presents a continuous downward trend and the regional vibration dispersion index presents a continuous downward trend or a consistent trend, check whether the daily load pattern data changes at the same period; According to the change of the daily load pattern data, adjust the judgment of the settlement risk.

[0008] Optionally, the calculation of the regional vibration activity index of the monitoring area comprises: Statistical analysis of the vibration data collected by each vibration sensor to identify and obtain local abnormal data; According to the local abnormal data, adjust its weight in the calculation of the regional vibration activity index, and perform weighted summation of the root mean square average value and the high frequency component energy average value of all vibration sensors in the region to obtain the regional vibration activity index.

[0009] Optionally, the calculation of the regional vibration dispersion index of the monitoring area comprises: high-pass filter the vibration data collected by each vibration sensor to obtain filtered vibration data; According to the filtered vibration data, calculate the root mean square value of the combined acceleration of each vibration sensor in a specific time period to obtain a root mean square value set; Perform outlier detection on the root mean square value set to identify and eliminate outliers in the root mean square value set to obtain a root mean square value set after eliminating outliers; Calculate the standard deviation of the root mean square value set after eliminating outliers to obtain the regional vibration dispersion index.

[0010] Optionally, the long-term trend monitoring of the regional vibration activity index and the regional vibration dispersion index of each monitoring area is performed, and a dynamic time window analysis method is used to determine whether the regional vibration activity index presents a continuous downward trend and whether the regional vibration dispersion index presents a continuous downward trend or a consistent trend, further comprising: Collect environmental monitoring data of the monitoring area, wherein the environmental monitoring data includes groundwater level, soil moisture, and surrounding construction activity intensity; According to the change of the environmental monitoring data, adjust the length of the dynamic time window and the trend judgment threshold for judging the trend of the regional vibration activity index and the regional vibration dispersion index; According to the occurrence rate of historical subsidence events and the corresponding vibration index change characteristics, adjust the starting point and ending point of the dynamic time window to determine whether the regional vibration activity index presents a continuous downward trend and whether the regional vibration dispersion index presents a continuous downward trend or a consistent trend.

[0011] Optionally, the calculation of the regional vibration activity index of the monitoring area further comprises: Identify the structural characteristics of each vibration sensor corresponding to the tile, and assign a structure correction coefficient to each vibration sensor according to the structural characteristics; Multiply the root mean square value of the combined acceleration calculated from the vibration data collected by each vibration sensor by the corresponding structure correction coefficient to obtain a corrected root mean square value; Multiply the high-frequency component energy extracted from the vibration data collected by each vibration sensor by the corresponding structure correction coefficient to obtain a corrected high-frequency component energy; Weighted sum the corrected root mean square average value and the corrected high-frequency component energy average value of all vibration sensors in the region to obtain the regional vibration activity index of the monitoring area.

[0012] Optionally, the computing obtains the regional vibration activity index of the monitoring area, further comprising: Baseline drift detection of the vibration data collected by each vibration sensor identifies systematic deviation caused by sensor performance attenuation; According to the systematic deviation, real-time calibration is performed on the vibration data collected by each vibration sensor to obtain calibrated vibration data; According to the calibrated vibration data, the root mean square value of the synthesized acceleration is calculated and the high-frequency component energy is extracted; The weighted sum of the calibrated root mean square average value of all vibration sensors in the region and the calibrated high-frequency component energy average value is obtained to obtain the regional vibration activity index of the monitoring area.

[0013] In a second aspect, the present application provides a pedestrian floor tile operation and maintenance management system based on big data analysis, which comprises: A data acquisition module divides the sidewalk network into monitoring areas and deploys multiple vibration sensors in each monitoring area according to a predetermined spatial distribution to collect vibration data of the floor tiles under daily load; An index calculation module periodically analyzes the vibration data in each monitoring area and calculates the regional vibration activity index and the regional vibration dispersion index of the monitoring area; A trend monitoring module monitors the long-term trends of the regional vibration activity index and the regional vibration dispersion index of each monitoring area, and uses a dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend and whether the regional vibration dispersion index shows a continuous downward trend or a consistent trend; A risk judgment module judges that the monitoring area has a settlement risk when it simultaneously identifies a continuous downward trend of the regional vibration activity index and a continuous downward trend or a consistent trend of the regional vibration dispersion index, generates and sends the settlement risk warning information.

[0014] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method provided in the first aspect when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method provided in the first aspect.

[0016] Compared with the related art, the pedestrian floor tile operation and maintenance management method and system based on big data analysis provided by the present application at least has the following technical effects: By dividing the sidewalk network into monitoring areas and deploying vibration sensors inside each monitoring area, the vibration data of the paving stones under daily load is collected, and the vibration data in each monitoring area is periodically analyzed to calculate the regional vibration activity index and the regional vibration dispersion index; By long-term trend monitoring of the two indexes and using dynamic time window analysis method, whether the regional vibration activity index presents a continuous downward trend and whether the regional vibration dispersion index presents a continuous downward trend or a consistent trend are determined; When both trends are identified, it is determined that the monitoring area has a settlement risk, and settlement risk warning information is generated, effectively solving the technical defects of the existing system in the face of large-scale, gradual roadbed hollowing caused by underground hidden factors.

[0017] By introducing the regional vibration activity index and the regional vibration dispersion index and long-term trend monitoring, the application can perceive the changes of the pavement state from the perspective of "whole" and "global"; The continuous decrease of the regional vibration activity index reflects the increase of the contact tightness of the paving stones as a whole with the underlying cushion, while the continuous decrease or consistent trend of the regional vibration dispersion index indicates the uniformity of the sinking of the paving stones as a whole. Combined with the two trends, the gradual and large-scale settlement caused by the loss of underground sand cushion can be accurately captured, even if there is no obvious crack or relative displacement on the surface of the paving stones, the early warning can be sent in time, the early and effective warning of the potential pavement collapse risk is realized, and the intelligent level of urban infrastructure operation and management and the public safety guarantee capability are improved.

[0018] The details of one or more embodiments of the application are given in the following drawings and description, so that other features, objects and advantages of the application are more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0019] The drawings described herein are intended to provide further understanding of the application, and form a part of the application. The illustrative embodiments of the application and their description serve to explain the application without constituting an improper limitation of the application. In the drawings: Figure 1 is a flowchart of a pedestrian paving stone operation and maintenance management method based on big data analysis according to an exemplary embodiment.

[0020] Figure 2 is a flowchart of step S3 according to an exemplary embodiment.

[0021] Figure 3 is a flowchart of the calculation of the regional vibration activity index in step S2 according to an exemplary embodiment.

[0022] Figure 4 is a flowchart of the calculation of the regional vibration dispersion index in step S2 according to an exemplary embodiment.

[0023] Figure 5 This is a flowchart illustrating step S3 according to another exemplary embodiment.

[0024] Figure 6 This is a block diagram illustrating a pedestrian paving tile operation and maintenance management system based on big data analysis, according to an exemplary embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0026] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0027] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0028] This operation and maintenance management system suffers from serious technical flaws. Its core reliance on individual data such as vibration and surface images of single paving stones allows it to identify only "local problems" but fails to detect "overall changes," thus making it unable to address systemic risks caused by hidden underground factors. For example, when hidden factors such as underground pipe leaks cause large-scale gradual erosion of the roadbed, the paving stones in the area will slowly and uniformly subside. Superficially, the relative positions of adjacent paving stones remain unchanged, the vibration response of individual paving stones maintains normal thresholds, and there are no cracks or abnormal gaps on the surface. In this situation, the operation and maintenance management system will continuously output the erroneous judgment that "the area is in good condition," leaving management departments completely unaware of the potential collapse risk. Such misjudgments directly lead to missed opportunities for optimal intervention. Once external factors such as heavy rain (which accelerates the liquefaction and loss of the subgrade) occur, it can easily trigger a chain reaction of road collapses (such as small vehicles triggering a critical point), causing serious public safety accidents. Improvement is urgently needed.

[0029] Based on the above, embodiments of the present invention provide a method and system for the operation and maintenance management of pedestrian paving stones based on big data analysis, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0030] Example 1

[0031] This invention provides a method for the operation and maintenance management of pedestrian paving stones based on big data analysis. Figure 1 This is a flowchart illustrating a pedestrian paving stone operation and maintenance management method based on big data analysis, according to an exemplary embodiment. Figure 1 As shown, the method includes: S1. Divide the sidewalk network into monitoring areas, and deploy multiple vibration sensors in each monitoring area according to a predetermined spatial distribution to collect vibration data of the paving stones under daily loads; In this embodiment, the monitoring area can be divided based on Geographic Information System (GIS) data, dividing the urban sidewalk into several independent areas with similar characteristics (such as geological conditions, traffic flow, construction date, etc.). For example, a main road sidewalk several kilometers long can be divided into several monitoring areas ranging from 500 meters to 1 kilometer in length. Sensors are deployed under or inside the paving stones to collect vibration signals of the paving stones in real time under daily loads from pedestrians, vehicles (such as street sweepers, shared bicycles, etc.). The vibration data typically includes information such as the frequency, amplitude, and duration of the vibration. The vibration sensors can be deployed in a grid layout, for example, in each monitoring area, vibration sensors are evenly deployed under or inside the paving stones at a spacing of 2 meters × 2 meters. These sensors are designed to continuously collect vibration data of the paving stones under daily loads; for example, when pedestrians pass by or small maintenance vehicles drive by, the sensors record the minute vibrations of the paving stones.

[0032] A pedestrian network refers to an interconnected pedestrian transportation system in a city, consisting of multiple pedestrian walkways paved with paving stones. A monitoring area, on the other hand, refers to an independent management unit within the pedestrian network, defined by factors such as geographical location, traffic flow, geological conditions, or historical settlement data. Therefore, each monitoring area is considered as a whole for condition assessment. Daily loads refer to the various external forces exerted on the pedestrian walkway during normal use, primarily including dynamic loads generated by pedestrian walking, cycling, and the passage of small maintenance vehicles. Vibration data refers to the raw signals collected by vibration sensors, reflecting the dynamic response of the paving stones under daily loads.

[0033] S2. Perform periodic comprehensive analysis on the vibration data in each monitoring area to calculate the regional vibration activity index and regional vibration dispersion index of the monitoring area. In this embodiment, the regional vibration activity index is a comprehensive indicator measuring the overall vibration intensity and frequency within a monitoring area, reflecting the overall response level of the paving stones under daily loads. A decrease in this index may indicate a tighter contact between the paving stones and the underlying supporting structure, or an increase in the overall stiffness of the foundation, which in some cases may be related to compaction during settlement. When calculating the regional vibration activity index, the vibration data collected by each vibration sensor can be preprocessed, such as removing noise and performing Fourier transforms to obtain frequency domain information. Subsequently, the root mean square (RMS) value of each sensor over a specific time period can be calculated, reflecting the vibration intensity. In this embodiment, the regional vibration activity index can be obtained by averaging or weighted averaging the RMS values ​​of all vibration sensors within the area. For example, the average RMS value of all sensors within the area can be calculated hourly as the regional vibration activity index for that hour.

[0034] The regional vibration dispersion index measures the degree of difference between data from various vibration sensors within a monitoring area, reflecting the uniformity of the vibration response of the paving stones in that area. A decrease or convergence of this index may indicate a change in the uniformity of the supporting structure beneath the paving stones; for example, uniform loss of the sand cushion layer may cause uniform settlement of the paving stones as a whole, resulting in a more uniform vibration response at each point. In this embodiment, the regional vibration dispersion index can be obtained by calculating the standard deviation of the root mean square (RMS) values. A larger standard deviation indicates higher dispersion, and vice versa. For example, the standard deviation of the combined RMS values ​​of acceleration from all sensors within the area can be calculated hourly as the regional vibration dispersion index for that hour.

[0035] S3. Long-term trend monitoring of the regional vibration activity index and the regional vibration dispersion index for each monitoring area, and using dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward or consistent trend. In this embodiment, the dynamic time window analysis method, as a time series analysis technique, allows the length and starting point of the analysis window to be dynamically adjusted based on data characteristics or external environmental factors to better capture changes in data trends. Long-term trend monitoring can be achieved through statistical methods such as moving averages and exponential smoothing. For example, the average values ​​of regional vibration activity indicators and regional vibration dispersion indicators over the past 7, 14, or 30 days can be calculated, and the changing trends of these average values ​​can be observed. The dynamic time window analysis method allows the system to dynamically adjust the length of the analysis window based on data volatility or external events (such as weather changes or construction activities). For example, when data fluctuations are large, a longer window can be used to smooth noise; when data changes drastically, a shorter window can be used for rapid response. Determining a continuous downward trend can be achieved by comparing the average value of the indicators within the current time window with the average values ​​of one or more previous time windows. If the average value of multiple consecutive time windows is lower than that of the previous window, a continuous downward trend can be identified. Determining a trend towards uniformity can be achieved by observing whether the standard deviation of the dispersion indicator continuously decreases and eventually converges to a small threshold range.

[0036] S4. When both the continuous downward trend of the regional vibration activity index and the continuous downward or converging trend of the regional vibration dispersion index are simultaneously identified, it is determined that there is a risk of settlement in the monitored area, and the settlement risk warning information is generated and sent.

[0037] In this embodiment, settlement risk early warning information refers to a notification automatically generated and sent to relevant management departments when the system determines that there is a settlement risk in the monitored area. This notification includes information such as the location of the settlement area, the risk level, and possible causes, enabling timely intervention. For example, if the regional vibration activity index of a monitored area shows a downward trend for 30 consecutive days, and the regional vibration dispersion index also shows a downward or converging trend for 30 consecutive days, the system will trigger a settlement risk early warning. The warning information may include the ID of the monitored area, the settlement risk level (e.g., low, medium, high), a trend chart, and suggested further inspection measures. This warning information can be sent to relevant management personnel via SMS, email, or a dedicated operation and maintenance management platform, enabling them to take timely measures such as on-site investigation, ground-penetrating radar detection, or repair and reinforcement, thereby effectively avoiding potential catastrophic accidents.

[0038] The implementation environment of the technical solutions in the above embodiments typically includes: a vibration sensor network deployed in the sidewalk tiles, a wireless communication module for data transmission, a cloud platform or local server for data storage and processing, and a user interface for data visualization and early warning information transmission. The entire system utilizes Internet of Things (IoT) technology to achieve real-time data acquisition, transmission, storage, analysis, and early warning, thereby constructing an intelligent tile operation and maintenance management system.

[0039] In the technical solution of the above embodiments, by introducing two macroscopic indicators, "regional vibration activity index" and "regional vibration dispersion index," and combining them with the "dynamic time window analysis method" for long-term trend monitoring, the perception and early warning of "overall" and "global" state changes are achieved. When underground hidden factors (such as the loss of sand cushion layer caused by underground pipeline leakage) cause large-scale, gradual roadbed erosion, the paving stones will settle synchronously and slowly as a whole. In this case, the vibration response of a single paving stone may not show drastic anomalies, but the vibration activity of the entire area will gradually decrease due to the compaction of the foundation. At the same time, due to the uniformity of settlement, the difference in vibration response between different paving stones will decrease, resulting in a uniform vibration dispersion. This application captures such subtle changes in "overall" and "global" conditions, thereby issuing early warnings in the early stages of settlement risk, buying valuable intervention time for management departments, and effectively solving the shortcomings of existing technologies in identifying large-scale, gradual settlement risks.

[0040] In one possible design, Figure 2 This is a flowchart illustrating step S3 according to an exemplary embodiment. (Refer to the attached diagram.) Figure 2 Step S3 includes: S301. Collect daily load pattern data within the monitoring area; In this embodiment, the daily load pattern data refers to external dynamic factors that affect the vibration response of pedestrian paving stones, such as pedestrian traffic, vehicle traffic frequency, and the number of times heavy equipment passes through within a specific time period. This data can be collected in various ways, such as through real-time or periodic collection using devices installed on the sidewalk, such as infrared sensors, video analytics systems, pressure sensors, or traffic counters.

[0041] S302. Correlate the daily load pattern data with the regional vibration activity index and the regional vibration dispersion index; In this embodiment, a correlation model between daily load pattern data and vibration indices is established using statistical methods or machine learning algorithms. For example, regression analysis, time series analysis, or neural network models can be used to learn the expected performance of vibration indices under different load patterns. The aim is to understand how vibration indices should fluctuate within the normal load variation range, thereby providing a benchmark for subsequent anomaly trend judgment.

[0042] S303. When the regional vibration activity index shows a continuous downward trend and the regional vibration dispersion index shows a continuous downward or consistent trend, check whether the daily load pattern data of the same period has changed. In this embodiment, a change can be defined as the statistical characteristics of daily load pattern data, such as the mean, peak value, or coefficient of variation, exceeding a certain threshold of the historical normal fluctuation range within a preset time window. For example, if the pedestrian traffic in a monitoring area suddenly decreases significantly during a certain period, this constitutes a change. The purpose is to identify non-settlement factors that may cause abnormal changes in vibration indicators.

[0043] S304. Adjust the assessment of settlement risk based on the changes in the daily load pattern data; In this embodiment, if the downward trend of the vibration index occurs simultaneously with the decrease in daily load pattern data, it may be necessary to lower the assessment level of settlement risk or extend the observation period to rule out the possibility of reduced vibration due to reduced load. Conversely, if the downward trend of the vibration index occurs while the daily load pattern data remains stable, the assessment of settlement risk is strengthened. This adjustment can be achieved by modifying the risk score, adjusting the warning threshold, or changing the urgency of the warning information, thereby improving the accuracy and reliability of settlement risk warnings and avoiding false alarms or missed alarms.

[0044] The technical solution described above fully considers the direct impact of external daily load pattern data on the vibration response of floor tiles. By incorporating daily load pattern data into the analysis, the system can more comprehensively understand the vibration behavior of floor tiles and effectively distinguish between vibration characteristic changes caused by floor tile settlement and those caused by changes in external load conditions. This reduces false alarms caused by fluctuations in the external environment, avoids unnecessary on-site inspections and resource waste, and ensures timely and accurate early warnings when actual settlement occurs.

[0045] In one example, suppose a monitoring area shows a continuous downward trend in both regional vibration activity and regional vibration dispersion indices over the past three months, initially indicating a risk of settlement. However, further analysis of daily load pattern data reveals that a large-scale municipal engineering project lasting two months was carried out nearby during the same period, resulting in temporary closure of sidewalks or a significant reduction in pedestrian traffic. In this situation, the system would identify a change in daily load pattern data (reduced pedestrian traffic). According to the proposed solution, the system would adjust its assessment of settlement risk, for example, changing the risk level from "high risk" to "medium risk," and recommending an extended observation period or a preliminary on-site investigation, rather than immediately initiating a comprehensive maintenance plan. After the municipal engineering project is completed, if the vibration index continues to decline after the daily load returns to normal, the settlement risk can be reconfirmed. Conversely, if the vibration index returns to normal, it indicates that the previous downward trend was mainly caused by changes in load patterns, thus avoiding a false alarm. In this way, the proposed solution can respond more intelligently and flexibly to complex real-world situations, improving the efficiency and accuracy of operation and maintenance management.

[0046] In one possible design, Figure 3 This is a flowchart illustrating the calculation of the regional vibration activity index in step S2 according to an exemplary embodiment. (Refer to the attached document.) Figure 3 The calculation of the regional vibration activity index of the monitoring area includes: S201. Statistical analysis of the vibration data collected by each vibration sensor is performed to identify and obtain local abnormal data; In this embodiment, local anomalous data may include, but is not limited to, instantaneous high-amplitude or anomalous frequency components caused by accidental heavy object drops, sudden vehicle braking, short-term construction vibrations, or momentary sensor malfunctions. Various statistical methods can be employed during the identification process, such as threshold-based methods, outlier detection algorithms (e.g., Z-score, IQR methods), or machine learning anomaly detection models.

[0047] S202. Based on the local anomaly data, adjust its weight in the calculation of the regional vibration activity index, and perform a weighted summation of the root mean square average of all vibration sensors in the region and the average energy of the high-frequency components to obtain the regional vibration activity index. In this embodiment, the weight adjustment can take various forms. For example, for data identified as anomalous, its weight can be reduced, or it can even be completely excluded from the calculation; or, a specific corrective weight can be assigned according to the degree of anomalousness. By adjusting the weight, the interference of local anomalous data on the overall regional vibration activity index can be weakened or eliminated, so that the index can more accurately reflect the overall vibration characteristics of the paving stones in the monitoring area.

[0048] In practical applications, the technical solution of the above embodiments involves a weighted summation of the root mean square (RMS) value of all vibration sensors within a given area and the average energy of the high-frequency components to obtain the regional vibration activity index. The RMS value reflects the overall energy level of the vibration signal, while the high-frequency component energy may be more relevant to local damage or loosening of the floor tiles. By weighting and summing these two components, the overall vibration intensity and local response characteristics of the floor tiles under daily loads can be comprehensively considered. The weights for the summation can be set based on practical experience, the characteristics of the floor tile material, or a model trained using historical data to optimize the index's sensitivity to settlement risk.

[0049] The technical solutions described above effectively avoid interference from local anomaly data in the calculation of regional vibration activity indicators, improving the accuracy and robustness of the indicators. This allows the obtained regional vibration activity indicators to more realistically and accurately reflect the actual stress state and structural stability of pedestrian paving stones, thus providing reliable data support for early identification and warning of settlement risks. Compared to solutions that do not consider anomaly data processing, this application effectively reduces the risk of false alarms and missed alarms, improving the intelligence level and decision-making efficiency of pedestrian paving stone operation and maintenance management.

[0050] In one example, suppose multiple vibration sensors are deployed within a monitoring area. During a monitoring period, most sensors collect vibration data within the normal range, reflecting the typical vibration pattern of the paving stones under pedestrian traffic. However, one sensor records a vibration peak significantly above average for a short period, possibly due to a heavy maintenance vehicle temporarily parked or a heavy object accidentally falling. If this anomalous data is not processed, it will inflate the root mean square (RMS) and high-frequency component energy averages of the area, causing an abnormally high calculated regional vibration activity index. This could be misinterpreted as increased activity of the paving stone structure, leading to unnecessary settlement risk warnings.

[0051] The technical solution of this embodiment first performs statistical analysis on the vibration data collected by each vibration sensor. For example, using the Z-score method with a sliding window, the instantaneous high vibration peak recorded by the sensor is identified as local abnormal data. Subsequently, when calculating the regional vibration activity index, this local abnormal data can be assigned a low weight, for example, its weight can be set to 10% of the normal data, or it can be directly excluded from the calculation of the average value for that time period. In this way, even if there are local abnormal events, the calculation result of the regional vibration activity index will not be severely distorted, and it can still accurately reflect the overall vibration activity of the paving stones in the monitored area.

[0052] In one possible design, Figure 4This is a flowchart illustrating the calculation of the regional vibration dispersion index in step S2 according to an exemplary embodiment. (Refer to the attached document.) Figure 4 The calculation of the regional vibration dispersion index of the monitoring area includes: S211. High-pass filtering is performed on the vibration data collected by each vibration sensor to obtain filtered vibration data; In this embodiment, high-pass filtering effectively removes low-frequency noise and static offset from the vibration data, thereby highlighting the transient vibration response of the paving stones under daily loads caused by vehicles, pedestrians, etc. This results in filtered vibration data that more accurately reflects the dynamic characteristics of the paving stones.

[0053] S212. Based on the filtered vibration data, calculate the root mean square value of the synthetic acceleration of each vibration sensor within a specific time period to obtain a set of root mean square values. In this embodiment, the root mean square (RMS) value of the synthesized acceleration quantifies the overall vibration intensity of the floor tiles within a specific time period. The RMS value of the synthesized acceleration comprehensively reflects the vibration energy across multiple axes, providing a unified quantitative basis for subsequent dispersion analysis. Thus, a set of RMS values ​​can be obtained.

[0054] S213. Perform outlier detection on the root mean square value set, identify and remove outliers from the root mean square value set, and obtain the root mean square value set after removing outliers. In this embodiment, outlier removal eliminates measurement biases caused by atypical events such as sensor malfunctions, instantaneous shocks, or environmental interference. Outlier detection can employ statistical methods, such as those based on interquartile range (IQR) or Z-score, to ensure that subsequent dispersion calculations are not affected by extreme data points, thereby obtaining the root mean square value set after outlier removal.

[0055] S214. Calculate the standard deviation of the root mean square value set after removing outliers to obtain the regional vibration dispersion index. In this embodiment, the standard deviation can accurately measure the dispersion of vibration intensity of bricks in the monitoring area. As a statistical quantity, the standard deviation can intuitively reflect the dispersion of data points relative to the mean, thereby obtaining the regional vibration dispersion index.

[0056] The technical solution described above effectively removes background noise and low-frequency interference by performing high-pass filtering on the raw vibration data, allowing subsequent analysis to focus more on the dynamic response of the floor tiles under actual loads. Based on this, the local vibration intensity of the floor tiles is quantified by calculating the root mean square (RMS) value of the composite acceleration of each vibration sensor, and these values ​​are aggregated into a set of RMS values. To ensure the accuracy of the dispersion index, outlier detection and removal are performed on this set to avoid interference from occasional extreme events on the overall assessment. Finally, by calculating the standard deviation of the set of RMS values ​​after outlier removal, the consistency or difference in vibration intensity of the floor tiles within the monitoring area can be objectively and accurately reflected.

[0057] In one possible design, Figure 5 This is a flowchart illustrating step S3 according to another exemplary embodiment. (Refer to the attached document.) Figure 5 Step S3 also includes: S311. Collect environmental monitoring data of the monitoring area, wherein the environmental monitoring data includes groundwater level, soil moisture and intensity of surrounding construction activities; In this embodiment, the environmental monitoring data refers to external environmental factors related to the risk of paving stone settlement. Among these, the groundwater level reflects the moisture content of the foundation soil; a high groundwater level may cause soil softening, increasing the risk of settlement. Soil moisture directly affects the physical and mechanical properties of the soil; excessively high or low moisture levels can affect foundation stability. The intensity of surrounding construction activities may have additional impacts on the paving stones through vibration, load changes, etc. The aforementioned environmental monitoring data can be collected in real time by deploying dedicated environmental sensors (such as groundwater level sensors and soil moisture sensors), or obtained through data interfaces with external meteorological and construction management systems.

[0058] S312. Based on the changes in the environmental monitoring data, adjust the length of the dynamic time window and the trend judgment threshold used to judge the trends of the regional vibration activity index and the regional vibration dispersion index. In this embodiment, when a continuous rise in groundwater level or an increase in soil moisture is detected, it indicates that the foundation soil may be in an unstable state. At this time, the length of the dynamic time window can be shortened and the trend judgment threshold can be lowered to improve the sensitivity and response speed to potential settlement risks. Conversely, when environmental conditions are stable, the window length can be appropriately extended or the threshold can be increased to reduce false alarms.

[0059] S313. Based on the occurrence rate of historical subsidence events and the corresponding vibration index change characteristics, adjust the start and end points of the dynamic time window to determine whether the regional vibration activity index shows a continuous downward trend and whether the regional vibration dispersion index shows a continuous downward or consistent trend. In this embodiment, the start and end points of the dynamic time window are adjusted using the occurrence rate of historical settlement events and the corresponding vibration index change characteristics. This allows the system to learn and remember how the vibration activity index and vibration dispersion index evolved during past settlement events. For example, if historical data shows that before settlement occurs in a certain area, the vibration activity index typically decreases at a specific rate over a specific time period, and the vibration dispersion index tends to converge, then in a new monitoring cycle, the system can more accurately set the start and end points of the dynamic time window based on these historical patterns, thereby capturing settlement-related vibration index changes earlier and more accurately.

[0060] The technical solution described above intelligently adjusts the parameters of the dynamic time window by incorporating environmental monitoring data and historical settlement event data. Environmental monitoring data provides information on the impact of the external environment on the stability of the paving stones, enabling trend judgments to be made in conjunction with actual working conditions. For example, during the rainy season or when there is large-scale construction nearby, the vibration characteristics of the paving stones may fluctuate normally. In this case, by adjusting the time window length and judgment threshold, normal fluctuations can be avoided from being misjudged as settlement risks. Simultaneously, the occurrence rate of historical settlement events and the corresponding vibration index changes allow the system to learn from past experience and identify vibration patterns that truly predict settlement. Therefore, the start and end points of the dynamic time window can be more accurately located, ensuring that the most critical vibration change signals are captured before settlement occurs, thereby improving the accuracy and timeliness of settlement risk warnings.

[0061] In one example, suppose that in a certain sidewalk monitoring area, the regional vibration activity index shows a continuous downward trend over a period of time, and the regional vibration dispersion index tends to be uniform. If only these vibration indicators are considered, the system may immediately issue a settlement risk warning.

[0062] The system proposed in this application first collects environmental monitoring data for the monitored area. For example, if the system simultaneously detects continuous heavy rainfall in the area over the past week, leading to a rise in groundwater levels and a significant increase in soil moisture, and there is no construction activity in the surrounding area, the system will determine, based on this environmental data, that the current change in vibration indicators may be partly attributable to the increase in soil moisture content, rather than simply foundation settlement. Therefore, the system will dynamically adjust the threshold for trend judgment; for example, by appropriately increasing the threshold for the magnitude of the decrease in vibration indicators used to assess settlement risk, or by extending the length of the dynamic time window to observe trends over a longer period. Simultaneously, the system will query a historical settlement event database and find that under similar rainfall conditions, the rate of decrease in vibration indicators in this area usually accelerates, but this does not necessarily lead to immediate settlement; rather, it requires a longer period of observation. Based on this information, the system can adjust the start and end points of the dynamic time window; for example, by pushing the window back a few days to eliminate interference from short-term environmental factors, thereby avoiding issuing unnecessary settlement risk warnings. Conversely, if the environmental data is normal, but the changes in vibration indicators highly match the characteristics of historical settlement events, the system will issue a warning earlier and more decisively.

[0063] In one possible design, step S2, calculating the regional vibration activity index of the monitoring area, further includes: S231. Identify the structural features of the floor tile corresponding to each vibration sensor, and assign a structural correction coefficient to each vibration sensor based on the structural features; In this embodiment, structural characteristics refer to the physical or engineering properties of the paving tiles, such as their material, size, thickness, laying method, service life, and the type of the underlying base layer. These characteristics directly affect the vibration response of the paving tiles under daily loads. For example, paving tiles of different materials (such as concrete, granite, and permeable bricks) or thicknesses will produce different vibration amplitudes and frequency characteristics under the same load. The structural correction factor is a value pre-set based on these structural characteristics or obtained through experimental calibration, used to correct for vibration data deviations caused by differences in paving tile structure. For example, for thinner or softer paving tiles, their vibration response may be higher; in this case, a larger correction factor can be assigned to avoid over-interpretation of their vibration data.

[0064] S232. Multiply the root mean square value of the composite acceleration calculated from the vibration data collected by each vibration sensor with its corresponding structural correction coefficient to obtain the corrected root mean square value. In this embodiment, the root mean square (RMS) value of the synthesized acceleration is a commonly used indicator for measuring vibration intensity, comprehensively reflecting the energy of the vibration in all directions; the high-frequency component energy focuses on reflecting the impact or local damage information contained in the vibration. By multiplying these original vibration indicators with the corresponding structural correction coefficients, the corrected RMS value and the corrected high-frequency component energy can be obtained. This correction aims to eliminate or reduce the influence of the structural characteristics of the floor tiles themselves on the vibration data, making the vibration data of different floor tiles under the same external load more comparable.

[0065] S233. Multiply the high-frequency component energy extracted from the vibration data collected by each vibration sensor with its corresponding structural correction coefficient to obtain the corrected high-frequency component energy. In this embodiment, vibration intensity and high-frequency impact characteristics are comprehensively considered to ensure that the final regional vibration activity index can more accurately reflect the actual vibration activity state of the entire paving stones within the monitoring area, rather than just the local vibration at the sensor location. The weights in the weighted summation can be optimized based on practical experience or through machine learning models to highlight vibration characteristics that are more sensitive to settlement risk.

[0066] S234. The corrected root mean square average value of all vibration sensors in the area and the corrected high-frequency component energy average value are weighted and summed to obtain the regional vibration activity index of the monitoring area.

[0067] In this embodiment, the structural characteristics of different floor tiles (such as material, thickness, and laying method) inherently affect the acquisition and analysis of vibration data. Without correction, this could lead to misjudgment of the actual vibration activity of the floor tiles. By introducing a structural correction coefficient, the bias caused by these structural differences can be effectively eliminated or reduced, allowing the corrected vibration data to more accurately reflect the dynamic response of the floor tiles under daily loads. Based on this, a weighted sum of the corrected root mean square average and the corrected high-frequency component energy average yields a more accurate and reliable regional vibration activity index.

[0068] The technical solution described above effectively solves the problem of inaccurate vibration activity index calculation due to differences in paving tile structure in traditional methods. By correcting the vibration data collected by each vibration sensor for structural characteristics, the influence of the paving tile's own structural characteristics on the vibration data can be eliminated or weakened, making the vibration data of different paving tiles under the same external load more comparable. Therefore, the calculated regional vibration activity index can more accurately reflect the actual vibration activity state of the overall paving tiles within the monitoring area, improving the accuracy and reliability of settlement risk assessment, avoiding false alarms or missed alarms due to structural differences, and thus enhancing the level of precision in the operation and maintenance management of pedestrian paving tiles.

[0069] In one possible design, step S2, calculating the regional vibration activity index of the monitoring area, further includes: S241. Detect baseline drift of vibration data collected by each vibration sensor and identify systematic deviations caused by sensor performance degradation; In this embodiment, baseline drift detection refers to identifying zero-point drift or long-term trend changes by analyzing the sensor's output signal under no-load or known stable load conditions. This drift is typically a systematic deviation caused by performance degradation due to factors such as aging of internal sensor components, changes in ambient temperature, or power supply fluctuations. Identifying the systematic deviation caused by sensor performance degradation can be understood as quantifying the degree and direction of baseline drift, for example, by calculating the average value of vibration data over a period of time, the slope of the trend line, or the deviation from a standard baseline.

[0070] S242. Based on the systematic deviation, the vibration data collected by each vibration sensor is calibrated in real time to obtain calibrated vibration data; In this embodiment, based on the systematic deviation, the vibration data collected by each vibration sensor is calibrated in real time. This can be achieved by subtracting the drift, applying a calibration coefficient, or using an adaptive filtering algorithm to adjust the original vibration data to its true physical value, thus obtaining calibrated vibration data. The purpose is to eliminate or reduce the impact of sensor performance degradation on data accuracy.

[0071] S243. Based on the calibrated vibration data, calculate the root mean square value of the synthesized acceleration and extract the high-frequency component energy; S244. The calibrated root mean square average value of all vibration sensors in the area is weighted and summed with the calibrated high-frequency component energy average value to obtain the regional vibration activity index of the monitoring area.

[0072] The technical solution described above effectively addresses the performance degradation problem that may occur due to long-term operation of vibration sensors by introducing baseline drift detection and real-time calibration of vibration data. When baseline drift or systematic deviation occurs in the sensors, baseline drift detection of the vibration data collected by each sensor can promptly identify and quantify the systematic deviation caused by sensor performance degradation. Subsequently, the vibration data is calibrated in real time based on the identified deviation, correcting the original data to calibrated vibration data that more closely reflects the actual situation. Based on this calibrated data, the root mean square value of the synthetic acceleration and the energy of the high-frequency components are calculated and weighted summed, ensuring that the final obtained regional vibration activity index accurately reflects the true vibration state of the floor tiles under daily loads, avoiding misjudgments caused by sensor malfunctions.

[0073] In one example, suppose that after a year of operation, the vibration sensor in a monitoring area no-load state no longer outputs a signal that is stable near zero, but instead shows a slow upward trend, indicating baseline drift. The technical solution of this application first performs baseline drift detection on the vibration data collected by the sensor. For example, the system can periodically compare the average value of the sensor output with the baseline value at the time of initial calibration during periods of low pedestrian traffic at night, and find a continuous positive deviation. After identifying this systematic deviation, the system will perform real-time calibration on the subsequently collected vibration data based on the deviation amount. For example, the deviation value is subtracted from the original data of each sampling point to obtain calibrated vibration data. Subsequently, based on these calibrated data, the root mean square value of the synthetic acceleration and the energy of the high-frequency components are calculated and weighted together with other calibrated sensor data to finally obtain an accurate regional vibration activity index. In this way, even if the sensor performance degrades, the accuracy of the activity index can be ensured, avoiding incorrect judgments of subsidence risk or ignoring real signs of subsidence due to sensor problems.

[0074] In summary, the pedestrian pavement maintenance and management method based on big data analysis provided in this invention introduces regional vibration activity and regional vibration dispersion indices and monitors their long-term trends. This allows for the perception of changes in pavement condition from both an "overall" and "global" perspective. A continuous decrease in the regional vibration activity index reflects an increase in the overall contact tightness between the pavement and the underlying subgrade, while a continuous decrease or convergence in the regional vibration dispersion index indicates the uniformity of overall pavement subsidence. Combining these two trends, the method can accurately detect gradual, large-scale settlement caused by the loss of the underground sand subgrade. Even without obvious cracks or relative displacement on the pavement surface, it can issue timely warnings, achieving early and effective early warning of potential pavement collapse risks. This enhances the intelligence level of urban infrastructure maintenance and management and improves public safety assurance capabilities.

[0075] Example 2 Embodiment 2 of this application provides a pedestrian paving tile operation and maintenance management system based on big data analysis. Figure 6 This is a block diagram illustrating a pedestrian paving tile operation and maintenance management system based on big data analytics, according to an exemplary embodiment. (See attached diagram.) Figure 6 The system includes: Data acquisition module 1 divides the sidewalk network into monitoring areas and deploys multiple vibration sensors in each monitoring area according to a predetermined spatial distribution to collect vibration data of the paving stones under daily loads. The index calculation module 2 performs periodic comprehensive analysis on the vibration data in each monitoring area to calculate the regional vibration activity index and the regional vibration dispersion index of the monitoring area. The trend monitoring module 3 performs long-term trend monitoring on the regional vibration activity index and the regional vibration dispersion index of each monitoring area, and uses a dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward trend or tends to be consistent. Risk assessment module 4, when simultaneously identifying a continuous downward trend in the regional vibration activity index and a continuous downward or converging trend in the regional vibration dispersion index, determines that there is a subsidence risk in the monitored area, and generates and sends the subsidence risk warning information.

[0076] In summary, the pedestrian pavement maintenance and management method and system based on big data analysis provided in this invention, by introducing regional vibration activity indicators and regional vibration dispersion indicators and monitoring their long-term trends, can perceive changes in pavement conditions from both an "overall" and "global" perspective. A continuous decrease in the regional vibration activity indicator reflects an increase in the overall contact tightness between the pavement and the underlying subgrade, while a continuous decrease or convergence in the regional vibration dispersion indicator indicates the uniformity of overall pavement subsidence. Combining these two trends, it can accurately detect gradual, large-scale settlement caused by the loss of the underground sand subgrade. Even if there are no obvious cracks or relative displacement on the pavement surface, it can issue timely warnings, achieving early and effective early warning of potential pavement collapse risks, and improving the intelligence of urban infrastructure operation and maintenance management and public safety assurance capabilities.

[0077] Example 3 Embodiment 3 of this application provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method provided in Embodiment 1 above.

[0078] Example 4 Embodiment 4 of this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method provided in Embodiment 1 above.

[0079] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0080] In a possible implementation, the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of implementing the method provided in Embodiment 1.

[0081] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0082] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0083] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for operation and maintenance management of pedestrian paving stones based on big data analysis, characterized in that, The method includes: The pedestrian network is divided into monitoring areas, and multiple vibration sensors are deployed in each monitoring area according to a predetermined spatial distribution to collect vibration data of the paving stones under daily loads. Periodic comprehensive analysis is performed on the vibration data within each monitoring area to calculate the regional vibration activity index and regional vibration dispersion index of the monitoring area. Long-term trend monitoring is performed on the regional vibration activity index and the regional vibration dispersion index of each monitoring area, and a dynamic time window analysis method is used to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward trend or tends to be consistent. When both the continuous downward trend of the regional vibration activity index and the continuous downward or converging trend of the regional vibration dispersion index are simultaneously identified, it is determined that there is a risk of subsidence in the monitored area, and the subsidence risk warning information is generated and sent.

2. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The long-term trend monitoring of the regional vibration activity index and the regional vibration dispersion index for each monitoring area, and the use of a dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward or converging trend, includes: Collect daily load pattern data within the monitoring area; The daily load pattern data are correlated with the regional vibration activity index and the regional vibration dispersion index; When the regional vibration activity index shows a continuous downward trend and the regional vibration dispersion index shows a continuous downward or consistent trend, check whether the daily load pattern data of the same period has changed. The assessment of settlement risk is adjusted based on changes in the daily load pattern data.

3. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The calculation of the regional vibration activity index of the monitoring area includes: Statistical analysis of the vibration data collected by each vibration sensor is performed to identify and obtain local abnormal data; Based on the local anomaly data, its weight in the calculation of the regional vibration activity index is adjusted, and the root mean square average of all vibration sensors in the region and the average energy of high-frequency components are weighted and summed to obtain the regional vibration activity index.

4. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The calculation of the regional vibration dispersion index of the monitoring area includes: The vibration data collected by each vibration sensor is high-pass filtered to obtain filtered vibration data; Based on the filtered vibration data, the root mean square value of the synthetic acceleration of each vibration sensor within a specific time period is calculated to obtain a set of root mean square values. Outlier detection is performed on the root mean square value set to identify and remove outliers from the root mean square value set, resulting in a root mean square value set after outlier removal. The standard deviation of the root mean square value set after removing outliers is calculated to obtain the regional vibration dispersion index.

5. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The method of long-term trend monitoring of the regional vibration activity index and the regional vibration dispersion index for each monitoring area, and using a dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward or uniform trend, further includes: Collect environmental monitoring data of the monitoring area, including groundwater level, soil moisture and intensity of surrounding construction activities; Based on the changes in the environmental monitoring data, adjust the length of the dynamic time window and the trend judgment threshold used to determine the trends of the regional vibration activity index and the regional vibration dispersion index; Based on the occurrence rate of historical subsidence events and the corresponding vibration index change characteristics, the start and end points of the dynamic time window are adjusted to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward or consistent trend.

6. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The calculation of the regional vibration activity index of the monitoring area also includes: Identify the structural features of the floor tile corresponding to each vibration sensor, and assign a structural correction coefficient to each vibration sensor based on the structural features; The root mean square value of the composite acceleration calculated from the vibration data collected by each vibration sensor is multiplied by its corresponding structural correction coefficient to obtain the corrected root mean square value. The high-frequency component energy extracted from the vibration data collected by each vibration sensor is multiplied by its corresponding structural correction coefficient to obtain the corrected high-frequency component energy. The regional vibration activity index of the monitoring area is obtained by weighted summing of the corrected root mean square average value of all vibration sensors in the area and the corrected high-frequency component energy average value.

7. The pedestrian paving tile operation and maintenance management method according to claim 1, characterized in that, The calculation of the regional vibration activity index of the monitoring area also includes: Baseline drift detection is performed on the vibration data collected by each vibration sensor to identify systematic deviations caused by sensor performance degradation; Based on the systematic deviation, the vibration data collected by each vibration sensor is calibrated in real time to obtain calibrated vibration data; Based on the calibrated vibration data, the root mean square value of the synthesized acceleration is calculated and the high-frequency component energy is extracted. The regional vibration activity index of the monitoring area is obtained by weighted summing of the calibrated root mean square average value of all vibration sensors in the area and the calibrated high-frequency component energy average value.

8. A pedestrian paving tile operation and maintenance management system based on big data analysis, characterized in that, The system includes: The data acquisition module divides the sidewalk network into monitoring areas and deploys multiple vibration sensors in each monitoring area according to a predetermined spatial distribution to collect vibration data of the paving stones under daily loads. The index calculation module performs periodic comprehensive analysis on the vibration data in each monitoring area to calculate the regional vibration activity index and the regional vibration dispersion index of the monitoring area. The trend monitoring module performs long-term trend monitoring on the regional vibration activity index and the regional vibration dispersion index of each monitoring area, and uses a dynamic time window analysis method to determine whether the regional vibration activity index shows a continuous downward trend, and whether the regional vibration dispersion index shows a continuous downward trend or tends to be consistent. The risk assessment module determines that there is a risk of subsidence in the monitored area when it simultaneously identifies a continuous downward trend in the regional vibration activity index and a continuous downward or converging trend in the regional vibration dispersion index, and generates and sends the subsidence risk warning information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images