Horizontal displacement intelligent monitoring method and system based on reciprocating inclinometer robot

Abstract

The application discloses a horizontal displacement intelligent monitoring method and system based on a reciprocating inclinometer robot, relates to the technical field of engineering safety monitoring, and comprises the following steps: dividing a monitoring area into a plurality of grid units, arranging and deploying a reciprocating inclinometer robot and an environment sensor in each grid unit; establishing a unified database, and storing horizontal displacement data collected by the robot and environment data collected by the environment sensor in each grid unit into the database in real time; statistically analyzing multi-source data in the database, judging the correlation between horizontal displacement changes and environment factors, and setting a dynamic environment interference threshold for each grid unit according to the correlation analysis result; and directly adopting displacement data collected by the robot to perform quantitative analysis on the grid unit which is not interfered by the environment or is less interfered by the environment. The application solves the problems that a traditional monitoring system is difficult to adapt to complex and changeable site working conditions and is prone to false alarms, missed alarms or early warning delays.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering safety monitoring, in particular to a horizontal displacement intelligent monitoring method and system based on a reciprocating inclinometer robot. BACKGROUND

[0002] In recent years, with the development of intelligent sensors, robot measurement platforms and data analysis technologies, automated and intelligent displacement monitoring methods have gradually emerged. Among them, the reciprocating inclinometer robot, as an automated measurement device suitable for linear or distributed areas such as tunnels, slopes, and foundation pits, has the advantages of controllable operation path, high repeatability, and easy network deployment, and has been gradually introduced into the field of horizontal displacement monitoring.

[0003] However, in actual application, due to the great interference of environmental factors (such as rainfall, temperature, wind speed, groundwater level fluctuation, etc.) on measurement data, it is difficult for the monitoring system to accurately identify the real structural displacement change. In addition, different grid areas are affected by geological structures, construction disturbances or operating loads, and the traditional method often uses a unified or static threshold for judgment, which is difficult to adapt to complex and variable field conditions, and is prone to false positives, false negatives or early warning delays.

[0004] Therefore, it is urgent to provide a horizontal displacement intelligent monitoring method and system that can integrate grid monitoring deployment, real-time data collection, multi-dimensional interference identification, and dynamic threshold determination mechanism to realize a more accurate, stable, and early warning capable geological displacement monitoring solution. SUMMARY

[0005] The present application aims to provide a horizontal displacement intelligent monitoring method and system based on a reciprocating inclinometer robot to solve the problems raised in the background.

[0006] To solve the above technical problems, the present application provides the following technical solution: a horizontal displacement intelligent monitoring method and system based on a reciprocating inclinometer robot, comprising the following steps:

[0007] Step S1: divide the monitoring area into several grid units, and arrange and deploy reciprocating inclinometer robots and environmental sensors in each grid unit;

[0008] Step S2: establish a unified database, and store the horizontal displacement data collected by the robots and the environmental data collected by the environmental sensors in each grid unit into the database in real time;

[0009] Step S3: statistically analyze the multi-source data in the database, judge the correlation between the horizontal displacement change and the environmental factors, and set a dynamic environmental interference threshold for each grid unit according to the correlation analysis result;

[0010] Step S4: For the grid cells that are not disturbed or less disturbed by the environment, directly use the displacement data collected by the robot for quantitative analysis; for the grid cells that are disturbed by the environment, according to the results of the correlation analysis of the environmental variables, correct the displacement data;

[0011] Step S5: According to the results of the quantitative analysis, set a safety threshold for the horizontal displacement of each grid cell, and when the displacement change of a certain grid cell exceeds the safety threshold, the system automatically sends a warning message.

[0012] According to the above technical solution, the step S3 further comprises:

[0013] Step S31: In each grid cell, select the historical horizontal displacement data in a preset time window and the environmental monitoring data in the corresponding time period, extract the change trend, and form a time series curve data set for comparison;

[0014] Step S32: Horizontally compare the horizontal displacement changes of multiple grid cells in similar time periods, identify grid cells that still have displacement abnormalities under similar environmental conditions, and mark the cells as disturbance sensitive cells;

[0015] Step S33: For the time series between each environmental factor and displacement change, set a delay window for observing causal clues, and when a certain environmental parameter jumps or continuously fluctuates, analyze whether displacement change is induced within the delay time, so as to judge the potential driving effect of the factor on displacement change;

[0016] Step S34: According to the frequency and amplitude of displacement fluctuation caused by each type of environmental factor in each grid cell, calculate the influence degree score, and use it as a reference basis for subsequent disturbance intensity evaluation;

[0017] Step S35: Preliminarily set the environmental disturbance threshold of each grid cell, and the threshold is set according to the typical time period in which the displacement fluctuation is frequent and consistent with the change of environmental factors in the historical data of the cell;

[0018] Step S36: During the monitoring process, when the environmental parameters monitored by a certain grid cell exceed the set disturbance threshold, automatically mark the displacement data in the time period as "possibly disturbed data".

[0019] According to the above technical solution, the step S34 further comprises:

[0020] Step S341: Divide the data of each type of environmental factor in each grid cell into preset time windows, extract the change amplitude, change frequency and duration of the environmental factor in each time window, and form an environmental change feature group;

[0021] Step S342: synchronously extract displacement change data in the corresponding time window, and assign a change level identifier to the window according to the severity of displacement fluctuation;

[0022] Step S343: statistically analyze the matching degree between the environmental feature group and the displacement level identifier in the plurality of time windows, and the statistical indicators include:

[0023] The proportion of significant displacement changes in the environment change significant window;

[0024] The incidence of abnormal displacement in the environment change stable window;

[0025] The approximate synchronization ratio between the environmental change amplitude and the displacement response amplitude;

[0026] Step S344: weighting and fusing the above statistical indicators according to the preset weight to obtain a reference coefficient of the influence of the environmental factor on the displacement in the grid unit;

[0027] Step S345: normalizing the reference coefficient into a percentage score value as the "influence degree score" of the environmental factor in the unit, and recording into the database for subsequent interference judgment and threshold adjustment reference;

[0028] Step S346: if a plurality of environmental factors are monitored, a set of score vectors is formed for each grid unit to evaluate the dominance of each factor interference, and when the score reaches a set limit value, a weight updating program is triggered.

[0029] According to the above technical solution, the step S4 further includes:

[0030] Step S41: for each grid unit, after each monitoring period, the system automatically determines the influence level of the unit according to whether the current environmental parameter exceeds the aforementioned set dynamic environmental interference threshold, and marks it as "negligible interference", "slight interference" or "significant interference";

[0031] Step S42: when the grid unit marked as "negligible interference" directly uses the horizontal displacement raw data collected by the robot, and enters the subsequent quantitative evaluation program for calculating the actual horizontal displacement value and trend evolution;

[0032] Step S43: when the grid unit marked as "slight interference" starts a mild correction process, including linear proportional correction of displacement data and current environmental factor fluctuation amplitude to generate preliminary compensation displacement data;

[0033] Step S44: When the grid cell marked as "significant interference", the system calls its historical data in similar environmental conditions under the displacement change record, generates a background control curve, and compares with the current acquisition curve, uses the correction factor to repair the current displacement data, and the repair result is marked as "environmental correction value".

[0034] According to the above technical scheme, the step S44 further comprises:

[0035] Step S441: After determining that a certain grid cell is "significant interference", the system automatically extracts the historical monitoring database of the grid cell, the environmental parameters and the historical time period similar to the current time period, and constructs a candidate sample set;

[0036] Step S442: From the candidate sample set, the historical sample section with the same trend direction of the horizontal displacement change trend and the displacement trend of the current time period is selected, and the number, duration and change amplitude are integrated to generate a historical background displacement curve as a "background control curve";

[0037] Step S443: The displacement curve acquired at present and the background control curve are synchronized, the starting point of the time axis and the data sampling interval are adjusted, so that they have comparability in time domain;

[0038] Step S444: The offset of the two curves at the corresponding time points is calculated, and a comprehensive offset weight factor is determined according to the overall offset mean, fluctuation amplitude and phase difference index;

[0039] Step S445: The offset weight factor is used to modify the data of each time node in the current acquisition displacement curve point by point, and the modification method is to compress, lift or translate each original displacement value according to the weight factor;

[0040] Step S446: The modified whole curve is marked as "environmental correction value curve", and is archived in the system database together with the original data, environmental data and offset comparison information for subsequent analysis and calling.

[0041] According to the above technical scheme, the step S5 further comprises:

[0042] Step S51: According to the historical monitoring data of each grid cell, the displacement change range of each grid cell under different time periods and different environmental conditions is respectively counted to form a typical displacement change curve group;

[0043] Step S52: Combined with the regional geological category, the underground structure type and the key risk level, different grid cells are classified and managed, and the reference safety threshold interval is respectively set;

[0044] Step S53: Compare the environment-corrected current displacement change value with the historical steady-state threshold interval of the corresponding grid cell. If the current value significantly deviates from the steady-state change range, enter the "early warning trigger candidate area";

[0045] Step S54: The system makes a comprehensive judgment on whether to trigger an early warning based on the following three dimensions:

[0046] (1). Whether the displacement change amplitude exceeds the upper limit of safety;

[0047] (2). Whether the displacement change rate exceeds the preset growth rate threshold;

[0048] (3). Whether the continuous abnormal duration exceeds the set time threshold;

[0049] Step S55: When any two or more indicators are met, the system automatically generates a "early warning event" for the grid cell, wherein the "early warning event" information includes: grid cell number, abnormal start time, abnormal duration, maximum change value, current level, comparison background curve number, and recommended response operation;

[0050] Step S56: The early warning information is pushed to the terminal of the corresponding responsible person after being encrypted by the system.

[0051] According to the above technical solution, the method for determining a comprehensive offset weight factor in step S444 specifically includes:

[0052] Step S4441: Obtain the current collected horizontal displacement time series , the background control curve is , which contains n sampling points, and the instantaneous offset is: ;

[0053] Step S4442: Calculate the overall offset mean, fluctuation amplitude, and stage difference index respectively, and the corresponding calculation expressions are:

[0054] The overall offset mean ;

[0055] The fluctuation amplitude ;

[0056] Divide the entire data into m consecutive time windows, calculate the local offset mean of each segment , and then obtain the maximum offset difference value between adjacent segments: ;

[0057] Step S4443: The calculation formula of the comprehensive offset weight factor is:

[0058] ;

[0059] wherein, is a positive real constant that adjusts sensitivity, the exponential function amplifies the effect of overall drift, so that large long-term drifts cause a rapid response; the logarithmic function controls the effect of noise fluctuations, so that high-frequency noise causes limited impact on the weight factor; the hyperbolic tangent function provides a boundary-enhanced response to episodic differences, so that sudden changes are highlighted but not excessively amplified.

[0060] A horizontal displacement intelligent monitoring system based on reciprocating inclinometer robot, comprising a grid deployment module, a data acquisition module, a database, a data analysis module, a data correction module and a safety warning module, the grid deployment module, the data acquisition module, the database, the data analysis module, the data correction module and the safety warning module are directly connected with each other; wherein,

[0061] The grid deployment module is used to divide the monitoring area into a plurality of grid units, and deploy reciprocating inclinometer robots and environmental sensors in each grid unit;

[0062] The data acquisition module is used to acquire displacement data and environmental data of each grid unit in real time;

[0063] The database is used to store the displacement data and environmental data collected by the data acquisition module, and support multi-dimensional correlation query operation based on time, position and parameter type;

[0064] The data analysis module is used to statistically analyze the multi-source time series data collected in the database, identify the correlation between horizontal displacement and environmental factors, and set a dynamic environmental interference threshold for each grid unit;

[0065] The data correction module is used to analyze and process the displacement data of the disturbed grid unit, identify the interference level, and perform different levels of data correction according to the influence degree of environmental variables;

[0066] The safety warning module is used to determine whether the current state of the grid unit is within the safety threshold range according to the corrected displacement change data, and when the continuous abnormality meets the set warning condition, the system automatically generates a warning event and pushes a notification.

[0067] According to the above technical scheme, the data correction module comprises an interference level determination unit, a historical data extraction unit and an offset factor calculation unit; wherein,

[0068] The interference level determination unit is used to divide the grid unit into three states of "negligible interference", "slight interference" or "significant interference" according to the comparison result of the current environmental parameters and the historical interference threshold.

[0069] The historical data extraction unit is suitable for extracting a historical time period sample similar to the current environmental condition from the database under a significant interference state, and constructing a background control curve;

[0070] The offset factor calculation unit is used to calculate a comprehensive offset weight factor according to the offset relationship between the current displacement curve and the background control curve.

[0071] According to the above technical solution, the safety warning module includes a historical template construction unit, a multi-dimensional evaluation unit and a warning generation unit; wherein,

[0072] The historical template construction unit is used to mine the typical horizontal displacement response characteristics of each grid unit under different environmental backgrounds based on long-term monitoring data, and induce the stable state change range to construct a historical curve set containing representative fluctuation patterns;

[0073] The multi-dimensional evaluation unit is used to evaluate the state from multiple dimensions in combination with the displacement behavior in the current monitoring period;

[0074] The warning generation unit is used to generate a warning record according to the evaluation result, and send it to the designated management terminal through the information system.

[0075] Compared with the prior art, the beneficial effects achieved by the present application are: the present application significantly improves the anti-interference and data reliability of displacement monitoring in complex environments through a dynamic environmental interference threshold mechanism and a hierarchical data correction strategy; further, based on multi-dimensional indexes such as displacement amplitude, change rate and abnormal duration, safety threshold values are set to realize intelligent risk assessment and automatic warning push, effectively solving the problems of high false alarm and missed alarm rate and poor environmental adaptability of traditional methods, and providing a high-precision, self-adaptive and low-manual-dependence displacement monitoring solution for slopes, tunnels and other projects. BRIEF DESCRIPTION OF DRAWINGS

[0076] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation of the present application. In the drawings:

[0077] Figure 1 A horizontal displacement intelligent monitoring method based on a reciprocating inclinometer robot is provided for the first embodiment of the present application, and a schematic diagram of the overall process is shown;

[0078] Figure 2 A horizontal displacement intelligent monitoring system framework diagram based on a reciprocating inclinometer robot is provided for the second embodiment of the present application;

[0079] Figure 3 A data correction module composition diagram is provided for the second embodiment of the present application;

[0080] Figure 4 The safety warning module provided for the second embodiment of the present application is shown in the schematic diagram. DETAILED DESCRIPTION

[0081] The technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0082] Embodiment one

[0083] Figure 1 The overall flowchart of the horizontal displacement intelligent monitoring method based on the reciprocating inclinometer robot provided for the first embodiment of the present application is shown in the schematic diagram.

[0084] In this embodiment, the method comprises the following steps:

[0085] Step S1: divide the monitoring area into a plurality of grid units, and arrange and deploy the reciprocating inclinometer robot and the environmental sensor in each grid unit; by dividing the monitoring area into a plurality of grid units and arranging the reciprocating inclinometer robot and the environmental sensor in each unit, the overall coverage of the complex terrain or the engineering area is realized, and the spatial resolution and the arrangement flexibility of the displacement monitoring are effectively improved.

[0086] Step S2: establish a unified database, and store the horizontal displacement data collected by the robot and the environmental data collected by the environmental sensor in each grid unit into the database in real time; by constructing the unified database, the real-time collected horizontal displacement data and the environmental factor monitoring data are fused, the specific source and the influence intensity of the environmental interference are identified through multi-dimensional statistics and causal analysis, so as to provide a basis for displacement data correction, and the reliability and the interpretability of the data are significantly improved;

[0087] Step S3: statistically analyze the multi-source data in the database, judge the correlation between the horizontal displacement change and the environmental factors, and set a dynamic environmental interference threshold for each grid unit according to the correlation analysis result; break through the limitation of the traditional static judgment standard, realize a more adaptive abnormal detection mechanism, and effectively reduce the false alarm and the missed alarm;

[0088] Step S4: for the grid unit which is not interfered by the environment or is less interfered by the environment, directly use the displacement data collected by the robot for quantitative analysis; for the grid unit interfered by the environment, correct the displacement data according to the result of the environmental variable correlation analysis;

[0089] Step S5: According to the results of quantitative analysis, set a safety threshold of horizontal displacement for each grid cell. When the displacement change of a certain grid cell exceeds the safety threshold, the system automatically issues a warning message.

[0090] Step S3 further comprises:

[0091] Step S31: In each grid cell, select historical horizontal displacement data within a preset time window and environmental monitoring data corresponding to the time period, extract the change trend, and form a time series curve data set for comparison;

[0092] Step S32: Horizontally compare the horizontal displacement changes of multiple grid cells within similar time periods, identify grid cells that still have displacement anomalies under similar environmental conditions, and mark the cells as interference sensitive cells;

[0093] Step S33: For the time series between each environmental factor and displacement change, set a delay window for observing causal clues. When a certain environmental parameter jumps or continuously fluctuates, analyze whether displacement change is induced within the delay time to determine the potential driving effect of the factor on displacement change;

[0094] Step S34: According to the frequency and amplitude of displacement fluctuations caused by each type of environmental factor in each grid cell, calculate the impact score, and use it as a reference basis for subsequent interference strength assessment;

[0095] Step S35: Preliminarily set the environmental interference threshold of each grid cell. The threshold is set according to the typical time period in the historical data of the cell where displacement fluctuations are frequent and highly consistent with environmental factor changes;

[0096] Step S36: During monitoring, when the environmental parameters monitored by a certain grid cell exceed its set interference threshold, automatically mark the displacement data within that time period as "possibly disturbed data".

[0097] Step S34 further comprises:

[0098] Step S341: Divide the data of each type of environmental factor in each grid cell into different time periods according to the preset time window, extract the change amplitude, change frequency, and duration of the environmental factor in each time window, and form an environmental change feature group;

[0099] Step S342: Simultaneously extract displacement change data within the corresponding time window, and assign a change level identifier to the window according to the severity of displacement fluctuation (such as change rate or jump amplitude);

[0100] Step S343: Statistics are performed on the matching degree between the environment feature group and the displacement level identifier in multiple time windows, and the statistics indicators include:

[0101] The proportion of significant displacement changes in the environment change significant window;

[0102] The incidence of displacement still being abnormal in the environment change smooth window;

[0103] Approximate synchronization ratio between the environment change amplitude and the displacement response amplitude;

[0104] Step S344: The above statistics indicators are weighted and fused according to the preset weight to obtain a reference coefficient of the influence of the environment factor on the displacement in the grid unit;

[0105] Step S345: The reference coefficient is normalized to a percentage score value as the “influence degree score” of the environment factor in the unit, and is recorded into the database for subsequent interference judgment and threshold adjustment reference; By statistically analyzing the matching degree between the environment factor and the displacement response, and combining the preset weight for weighted fusion, the influence degree of different environment variables on the displacement data can be effectively quantified. The multi-dimensional indicators not only consider the direct driving of significant environmental events on displacement, but also include atypical causes of displacement anomalies, which helps to establish a more stable and comprehensive interference discrimination model, thereby realizing the quantitative evaluation of the credibility of displacement data under complex interference background, effectively improving the automatic correction ability and anti-interference performance of the system under non-ideal environment, and reducing the false alarm rate;

[0106] Step S346: If multiple environment factors are monitored, a set of score vectors is formed for each grid unit to evaluate the dominance of each factor interference, and when the score reaches the set limit value, a weight updating program is triggered.

[0107] Step S4 further comprises:

[0108] Step S41: For each grid unit, after each monitoring period ends, the system automatically determines the influence level of the unit according to whether the current environmental parameter exceeds the aforementioned set dynamic environmental interference threshold, and marks it as “interference can be ignored”, “slight interference” or “significant interference”;

[0109] Step S42: When the grid unit marked as “interference can be ignored”, directly use the horizontal displacement raw data collected by the robot, and enter the subsequent quantitative evaluation program to calculate the actual horizontal displacement value and trend evolution;

[0110] Step S43: When the grid unit marked as “slight interference”, start the light correction process, including linear proportional correction of the displacement data and the current environment factor fluctuation amplitude to generate preliminary compensation displacement data;

[0111] Step S44: When the grid cell marked as "significant interference", the system calls its historical data in similar environmental conditions under the displacement change record, generates background contrast curve, and compares with the current acquisition curve, uses the correction factor to repair the current displacement data, and the repair result is marked as "environmental correction value"; For different interference levels, the system respectively adopts mild linear correction and deep repair strategy based on historical contrast curve, combined with offset factor calculation model, to reasonably correct the disturbed data, so that the monitoring data can still maintain stability and representativeness under strong environmental fluctuation background.

[0112] Step S44 further comprises:

[0113] Step S441: After determining that a certain grid cell is "significant interference", the system automatically extracts the historical monitoring database of the grid cell, the historical time period with similar environmental parameters and the current time period, and constructs a candidate sample set;

[0114] Step S442: From the candidate sample set, the historical sample section with the same displacement trend direction as the current time period is selected, and the number, duration and change amplitude are combined to generate a historical background displacement curve as a "background contrast curve";

[0115] Step S443: The displacement curve currently collected and the background contrast curve are synchronized, the starting point of the time axis and the data sampling interval are adjusted, so that they have comparability in the time domain;

[0116] Step S444: Calculate the offset of the two curves at the corresponding time points, and determine a comprehensive offset weight factor according to the overall offset mean, fluctuation amplitude and phase difference index;

[0117] Step S445: Use the offset weight factor to modify the data of each time node in the current acquisition displacement curve point by point, and the modification method is to compress, lift or translate each original displacement value according to the weight factor;

[0118] Step S446: The modified whole curve is marked as "environmental correction value curve", and is archived in the system database together with the original data, environmental data and offset comparison information for subsequent analysis and calling.

[0119] Step S5 further comprises:

[0120] Step S51: According to the historical monitoring data of each grid cell, the displacement change range under different time periods and different environmental conditions is respectively counted to form a typical displacement change curve group;

[0121] Step S52: Based on the regional geological category, underground structure type and key risk level, different grid units are classified and managed, and the baseline safety threshold interval is set respectively;

[0122] Step S53: The current displacement change value after environmental correction is compared with the historical steady-state threshold interval of the corresponding grid unit. If the current value deviates significantly from the steady-state change range, it enters the "early warning trigger candidate area";

[0123] Step S54: The system makes a comprehensive judgment whether to trigger an early warning based on the following three dimensions:

[0124] (1). Whether the displacement change amplitude exceeds the upper limit of safety;

[0125] (2). Whether the displacement change rate exceeds the preset growth rate threshold;

[0126] (3). Whether the continuous abnormal duration exceeds the set time threshold;

[0127] Step S55: When any two or more indicators are met, the system automatically generates a "early warning event" for the grid unit, wherein the "early warning event" information includes: grid unit number, abnormal start time, abnormal duration, maximum change value, current level, comparison background curve number and recommended response operation;

[0128] Step S56: The early warning information is pushed to the corresponding responsible person terminal after being encrypted by the system; a multi-dimensional evaluation model is constructed based on the three dimensions of displacement amplitude, change rate and abnormal duration, forming a more comprehensive abnormal judgment standard. When multiple indicators exceed the limit at the same time, detailed early warning event information is automatically generated and pushed to the responsible terminal, realizing closed-loop control from monitoring to response, and improving the automation and intelligence level of the system.

[0129] In step S444, a method for determining a comprehensive offset weight factor includes:

[0130] Step S4441: Obtain the current collected horizontal displacement time series , the background control curve is , which contains n sampling points, then the instantaneous offset is: ;

[0131] Step S4442: Calculate the overall offset mean, fluctuation amplitude and stage difference index respectively, and the corresponding calculation expressions are:

[0132] The overall offset mean ;

[0133] The fluctuation amplitude ;

[0134] Divide the whole data into m continuous time windows, calculate the local offset mean value of each segment Then the maximum offset difference between adjacent segments is obtained: ;

[0135] Step S4443: Comprehensive offset weight factor The calculation formula is:

[0136] ;

[0137] Wherein, is a positive real constant for adjusting sensitivity, which can be trained offline or calibrated by experts, the exponential function is used to amplify the influence of the overall offset, so that large long-term offset can quickly cause a response; the logarithmic function controls the influence of noise fluctuation, so that slight changes caused by high-frequency noise have limited impact on the weight factor; the hyperbolic tangent function provides a boundary-enhanced response to the phase difference, so that sudden changes are highlighted but not over-amplified.

[0138] Embodiment two

[0139] Figure 2 A horizontal displacement intelligent monitoring system framework based on reciprocating inclinometer robot is provided for the second embodiment of the application.

[0140] In this embodiment, the system comprises a grid deployment module, a data acquisition module, a database, a data analysis module, a data correction module and a safety warning module, which are directly connected in communication with each other; wherein,

[0141] The grid deployment module is used to divide the monitoring area into a plurality of grid units, and deploy reciprocating inclinometer robots and environmental sensors in each grid unit.

[0142] The data acquisition module is used to acquire displacement data and environmental data of each grid unit in real time.

[0143] The database is used to store the displacement data and environmental data collected by the data acquisition module, and supports multi-dimensional correlation query operation based on time, position and parameter type.

[0144] The data analysis module is used to statistically analyze the multi-source time series data collected in the database, identify the correlation between horizontal displacement and environmental factors, and set a dynamic environmental interference threshold for each grid unit.

[0145] The data correction module is used for analyzing and processing displacement data of the disturbed grid unit, identifying the interference level, and performing different levels of data correction according to the influence degree of the environmental variable;

[0146] The safety warning module is used for judging whether the current state of the grid unit is within the safety threshold range according to the corrected displacement change data, and when the continuous anomaly meets the set warning condition, the system automatically generates a warning event and pushes a notification.

[0147] Figure 3 The data correction module provided for the second embodiment of the present application has a composition schematic diagram as shown in Figure 3 The data correction module includes an interference level judgment unit, a historical data extraction unit and an offset factor calculation unit; wherein,

[0148] The interference level judgment unit is used for dividing the grid unit into three states of "negligible interference", "slight interference" or "significant interference" according to the comparison result of the current environmental parameter and the historical interference threshold;

[0149] The historical data extraction unit is applicable to the significant interference state, extracts historical time period samples similar to the current environmental condition from the database, and constructs a background comparison curve;

[0150] The offset factor calculation unit is used for calculating a comprehensive offset weight factor according to the offset relationship between the current displacement curve and the background comparison curve.

[0151] Figure 4 The safety warning module provided for the second embodiment of the present application has a composition schematic diagram as shown in Figure 4 The safety warning module includes a historical template construction unit, a multi-dimensional evaluation unit and a warning generation unit; wherein,

[0152] The historical template construction unit is used for mining typical horizontal displacement response characteristics of each grid unit under different environmental backgrounds based on long-term monitoring data, inducing the steady-state change range, and constructing a historical curve set containing representative fluctuation patterns;

[0153] The multi-dimensional evaluation unit is used for combining the displacement behavior in the current monitoring period to perform state evaluation from multiple dimensions;

[0154] The warning generation unit is used for generating a warning record according to the evaluation result, and sending it to the designated management terminal through the information system;

[0155] The application significantly improves the anti-interference and data reliability of displacement monitoring in a complex environment through a dynamic environmental interference threshold mechanism and a hierarchical data correction strategy; further, based on multi-dimensional indexes such as displacement amplitude, change rate and abnormal duration, a safety threshold is set to realize intelligent risk assessment and automatic early warning push, effectively solving the problems of high false alarm and missed alarm rate and poor environmental adaptability of traditional methods, and providing a high-precision, self-adaptive and low-labor-dependent displacement monitoring solution for slopes, tunnels and other projects.

[0156] The application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0157] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0158] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowcharts and / or block diagrams.

[0159] The embodiments of the application are described above in combination with the drawings, but the application is not limited to the above specific embodiments, and the above specific embodiments are only illustrative, not limiting, and those skilled in the art can make many forms under the inspiration of the application without departing from the purpose of the application and the scope protected by the claims.

Claims

1. A method for intelligent monitoring of horizontal displacement based on a reciprocating inclinometer robot, characterized in that, Includes the following steps: Step S1: Divide the monitoring area into several grid cells, and deploy a reciprocating inclinometer robot and environmental sensors in each grid cell; Step S2: Establish a unified database to store the horizontal displacement data collected by the robot and the environmental data collected by the environmental sensors in each grid cell in real time. Step S3: Perform statistical analysis on the multi-source data in the database to determine the correlation between horizontal displacement changes and environmental factors, and set a dynamic environmental disturbance threshold for each grid cell based on the correlation analysis results; Step S4: For grid cells that are not affected by environmental interference or are marked as "interference negligible", the displacement data collected by the robot is directly used for quantitative analysis. For grid cells affected by environmental disturbances, the displacement data is corrected based on the results of the environmental variable correlation analysis. Step S4 further includes: Step S41: For each grid cell, at the end of each monitoring cycle, the system automatically determines the impact level of the cell based on whether the current environmental parameters exceed the aforementioned dynamic environmental interference threshold, and marks it as one of three states: "interference negligible", "minor interference" or "significant interference". Step S42: For grid cells marked as "negligible interference", the original horizontal displacement data collected by the robot is directly accepted and entered into the subsequent quantitative evaluation program to calculate the actual horizontal offset value and trend evolution. Step S43: When a grid cell is marked as "slightly disturbed", a mild correction process is initiated, including linear scaling correction of the displacement data with the fluctuation amplitude of the current environmental factors, and generating preliminary compensated displacement data; Step S44: When a grid cell is marked as "significant disturbance", the system calls the displacement change records in its historical data under similar environmental conditions, generates a background comparison curve, compares the offset with the currently acquired curve, and uses a correction factor to repair the current displacement data. The repair result is marked as "environmental correction value". Step S5: Based on the results of the quantitative analysis, a safety threshold for horizontal displacement is set for each grid cell. When the displacement change of a certain grid cell exceeds the safety threshold, the system automatically issues an early warning message.

2. The intelligent horizontal displacement monitoring method based on a reciprocating inclinometer robot according to claim 1, characterized in that: Step S3 further includes: Step S31: Within each grid cell, select historical horizontal displacement data within a preset time window and environmental monitoring data for the corresponding time period, extract their changing trends, and form a time series curve data set for comparison. Step S32: Perform a lateral comparison of the horizontal displacement changes of multiple grid cells within similar time periods, identify grid cells that still exhibit abnormal displacement under similar environmental conditions, and mark these cells as disturbance-sensitive cells; Step S33: For the time series between various environmental factors and displacement changes, set a delay window for observing causal clues. When a certain environmental parameter shows a jump or continuous fluctuation, analyze whether it induces displacement changes within the delay time, thereby judging the potential driving effect of the factor on displacement changes. Step S34: Calculate the impact score based on the frequency and amplitude of displacement fluctuations caused by each type of environmental factor in each grid cell, and use this as a reference for subsequent disturbance intensity assessment. Step S35: Initially set the environmental disturbance threshold for each grid cell. The threshold is set based on a typical time period in the historical data of the cell where displacement fluctuations are frequent and highly consistent with changes in environmental factors. Step S36: During the monitoring process, when the environmental parameters monitored by a certain grid cell exceed its set interference threshold, the displacement data within that time period is automatically marked as "data that may be disturbed".

3. The intelligent horizontal displacement monitoring method based on a reciprocating inclinometer robot according to claim 2, characterized in that: Step S34 further includes: Step S341: Divide the data of each type of environmental factor in different time periods within each grid cell according to a preset time window, and extract the change amplitude, change frequency and duration of the environmental factor in each time window to form an environmental change feature group. Step S342: Synchronously extract displacement change data within the corresponding time window, and assign a change level label to the window according to the severity of displacement fluctuations; Step S343: Statistically analyze the matching degree between environmental feature groups and displacement level identifiers across multiple time windows. Statistical indicators include: The percentage of cases where significant displacement changes occur within a significant window of environmental change; The incidence of abnormal displacement within a stable environmental change window; The approximate synchronization ratio between the magnitude of environmental change and the magnitude of displacement response; Step S344: The above statistical indicators are weighted and fused according to preset weights to obtain the reference coefficient of the environmental factor's influence on displacement in the grid cell; Step S345: Normalize the reference coefficients into percentage scores, which serve as the "impact score" of the environmental factor within the unit, and record them in the database for subsequent interference judgment and threshold adjustment reference; Step S346: If multiple environmental factors are monitored, a set of score vectors is formed for each grid cell to assess the dominance of each factor's interference, and a weight update procedure is triggered when the score reaches a set threshold value.

4. The intelligent horizontal displacement monitoring method based on a reciprocating inclinometer robot according to claim 1, characterized in that: Step S44 further includes: Step S441: After determining that a certain grid cell is a "significant disturbance", the system automatically extracts historical time periods with environmental parameters similar to the current time period from the historical monitoring database of that grid cell to construct a candidate sample set; Step S442: Select historical sample segments from the candidate sample set whose horizontal displacement change trend matches the displacement trend direction of the current time period, and generate a historical background displacement curve by combining their quantity, duration and change amplitude, as a "background control curve"; Step S443: Synchronize the currently acquired displacement curve with the background comparison curve, and adjust the starting point of the time axis and the data sampling interval to make the two comparable in the time domain; Step S444: Calculate the offset of the two curves at the corresponding time points, and determine a comprehensive offset weighting factor based on the overall offset mean, fluctuation range, and stage difference index. Step S445: Use the offset weighting factor to correct the data of each time node in the currently acquired displacement curve point by point. The correction method is to perform amplitude compression, boosting or translation operation on each original displacement value according to the weighting factor. Step S446: The corrected curve is marked as "Environmental Correction Value Curve" and archived in the system database along with the original data, environmental data, and offset comparison information for subsequent analysis.

5. The intelligent horizontal displacement monitoring method based on a reciprocating inclinometer robot according to claim 1, characterized in that: Step S5 further includes: Step S51: Based on the historical monitoring data of each grid unit, statistically analyze the displacement change range of each unit under different time periods and environmental conditions to form a typical displacement change curve family. Step S52: Based on the regional geological category, underground structure type and key risk level, classify and manage different grid units, and set benchmark safety threshold ranges for each; Step S53: Compare the current displacement change value after environmental correction with the historical steady-state threshold range of the corresponding grid cell. If the current value deviates significantly from the steady-state change range, enter the "early warning trigger candidate area". Step S54: The system makes a comprehensive judgment based on the following three dimensions to determine whether to trigger an alert: (1) Does the displacement change exceed the safety limit? (2). Does the rate of displacement change exceed the preset growth rate threshold? (3) Does the duration of continuous abnormality exceed the set time threshold? Step S55: When any two or more indicators are met, the system automatically generates an "early warning event" for the grid cell. The "early warning event" information includes: grid cell number, anomaly start time, anomaly duration, maximum change value, current level, comparison background curve number, and suggested response operation. Step S56: The warning information is encrypted by the system and then pushed to the terminal of the corresponding person in charge.

6. The intelligent horizontal displacement monitoring method based on a reciprocating inclinometer robot according to claim 4, characterized in that: In step S444, the method for determining a comprehensive offset weighting factor specifically includes: Step S4441: Obtain the currently acquired horizontal displacement time series. The background contrast curve is If there are n sampling points, then the instantaneous offset is: ; Step S4442: Calculate the overall mean offset, fluctuation range, and periodic difference index respectively. The corresponding calculation expressions are as follows: Overall offset mean ; Fluctuation range ; Divide the entire data segment into m consecutive time windows and calculate the mean local offset for each segment. Then, the maximum offset difference between adjacent segments is obtained: ; Step S4443: Comprehensive offset weighting factor The calculation formula is: ； in, A positive real constant used to adjust sensitivity.

7. A horizontal displacement intelligent monitoring system based on a reciprocating inclinometer robot, characterized in that: The intelligent horizontal displacement monitoring system includes a grid deployment module, a data acquisition module, a database, a data analysis module, a data correction module, and a safety early warning module. These modules are directly interconnected. The grid deployment module is used to divide the monitoring area into several grid units, and to deploy a reciprocating inclinometer robot and environmental sensors in each grid unit. The data acquisition module is used to collect displacement data and environmental data of each grid cell in real time; The database is used to store the displacement data and environmental data collected by the data acquisition module, and supports multi-dimensional related query operations based on time, location and parameter type. The data analysis module is used to perform statistical analysis on multi-source time series data collected in the database, identify the correlation between horizontal displacement and environmental factors, and set the dynamic environmental disturbance threshold for each grid cell. The data correction module is used to analyze and process the displacement data of the disturbed grid cells, identify the interference level, and perform different levels of data correction according to the degree of influence of environmental variables. For each grid cell, at the end of each monitoring cycle, the system automatically determines the impact level of the cell based on whether the current environmental parameters exceed the aforementioned dynamic environmental interference threshold, marking it as one of three states: "negligible interference," "slight interference," or "significant interference." When a grid cell is marked as "negligible interference," the original horizontal displacement data collected by its robot is directly adopted and enters the subsequent quantitative evaluation program to calculate the actual horizontal offset value and trend evolution. When a grid cell is marked as "slight interference," a mild correction process is initiated, including linear proportional correction of the displacement data and the fluctuation amplitude of the current environmental factors to generate preliminary compensation displacement data. When a grid cell is marked as "significant interference," the system calls the displacement change records in its historical data under similar environmental conditions to generate a background comparison curve, compares the offset with the currently collected curve, and uses a correction factor to repair the current displacement data. The repair result is marked as "environmental correction value." The safety early warning module is used to determine whether the current state of the grid cell is within the safety threshold range based on the corrected displacement change data. When continuous anomalies meet the set early warning conditions, the system automatically generates an early warning event and pushes a notification.

8. The intelligent horizontal displacement monitoring system based on a reciprocating inclinometer robot according to claim 7, characterized in that: The data correction module includes an interference level determination unit, a historical data extraction unit, and a offset factor calculation unit; wherein... The interference level determination unit is used to divide the grid cells into three states: "negligible interference", "slight interference" or "significant interference" based on the comparison results between the current environmental parameters and historical interference thresholds. The historical data extraction unit is suitable for extracting historical time period samples similar to the current environmental conditions from the database under significant interference conditions, and constructing a background control curve. The offset factor calculation unit is used to calculate a comprehensive offset weight factor based on the offset relationship between the current displacement curve and the background comparison curve.

9. The intelligent horizontal displacement monitoring system based on a reciprocating inclinometer robot according to claim 7, characterized in that: The security early warning module includes a historical template construction unit, a multi-dimensional evaluation unit, and an early warning generation unit; wherein... The historical template construction unit is used to mine the typical horizontal displacement response characteristics of each grid unit under different environmental backgrounds based on long-term monitoring data, summarize its steady-state change range, and construct a set of historical curves containing representative fluctuation patterns. The multi-dimensional evaluation unit is used to perform state evaluation from multiple dimensions by combining the displacement behavior within the current monitoring period; The early warning generation unit is used to generate early warning records based on the evaluation results and send them to the designated management terminal through the information system.

Images