Dynamic environment settlement observation method

Abstract

The invention relates to a dynamic environment settlement observation method, and relates to the technical field of data analysis, high-precision equipment is used for collecting settlement data and environment data in a settlement area, the timestamps, monitoring point numbers, temperature and humidity information of the data are recorded, and the settlement data and the environment data of the settlement area are preprocessed; the method comprises the steps of processing monitoring points, storing processed data in a database, extracting newly stored settlement data and environment data from the database, merging the settlement data and the environment data to form a new data set, calculating the settlement rate of each time period for each monitoring point, forming a settlement rate time sequence, performing trend analysis, and determining the settlement rate of each monitoring point. And constructing a settlement prediction model according to the settlement data and the analysis result, setting a dynamic settlement early warning threshold value based on the prediction result, when the monitoring data exceeds the early warning threshold value, triggering an alarm, checking whether the settlement height of each monitoring point exceeds the early warning threshold value, marking the monitoring point which triggers early warning as a settlement abnormal area, and generating a monitoring report.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and more specifically, to a dynamic environmental settlement observation method. Background Art

[0002] With the acceleration of global urbanization, the continuous expansion of urban infrastructure and the rapid changes in land use, the problem of ground subsidence has become increasingly prominent. Ground subsidence refers to the gradual sinking of the surface or base of the earth due to natural or human activities. The reasons behind it are varied, especially under the combined effects of excessive exploitation of groundwater resources, drastic changes in soil moisture, and construction sites. The risk of subsidence is increasing. This not only poses challenges to urban resource management and sustainable development, but also directly affects public safety, and may cause damage to infrastructure such as roads, bridges, and buildings, resulting in economic losses and social problems.

[0003] Traditional static measurement methods are often unable to capture and reflect the settlement changes in a dynamic environment due to their time lag and lack of accuracy. Therefore, the development of a new type of dynamic environmental settlement observation method can achieve real-time monitoring and data analysis of settlement conditions, and provide timely and accurate information support for relevant departments so that they can respond quickly and take necessary countermeasures. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a dynamic environmental settlement observation method to solve the problems raised in the above-mentioned background technology.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: a dynamic environmental sedimentation observation method, specifically comprising the following steps:

[0006] Step 101: Collect settlement data and environmental data of the settlement area, perform preprocessing, and store the processed data in a database;

[0007] Step 102, analyzing the settlement data and environmental data stored in the database to calculate the settlement rate and trend;

[0008] Step 103: construct a settlement prediction model based on the settlement data and analysis results, and set a settlement warning threshold based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered;

[0009] Step 104: According to the settlement warning threshold calculation method of step 103, check whether the settlement height of each monitoring point exceeds the warning threshold, mark the monitoring point that triggers the warning as an abnormal settlement area, and generate a monitoring report.

[0010] In a preferred embodiment, in step 101, the settlement data and environmental data of the settlement area are collected and preprocessed, and the processed data are stored in a database. The specific steps are as follows:

[0011] Step A1, data collection: using high-precision equipment including GPS equipment, laser rangefinder, environmental sensor to collect settlement data and environmental data in the settlement area, and record the timestamp, monitoring point number, temperature, humidity information of the data, further including the following steps:

[0012] Step A101: determine the land subsidence area to be monitored, construct an electronic map of the area, mark key infrastructure, terrain features and monitoring point locations, and divide the monitoring area into multiple sub-areas on the electronic map;

[0013] Step A102: deploying settlement monitoring points in each sub-area and installing settlement monitoring equipment at the monitoring points to monitor the change of ground height in real time;

[0014] Step A103, setting the frequency and time interval of data collection to collect settlement data and environmental data once every hour, including settlement height, timestamp, monitoring point number, temperature and humidity information;

[0015] Step A2, preprocessing: perform a preliminary check on the collected raw data, identify and remove outliers and erroneous data, use interpolation to complete the missing data to maintain data continuity, create a settlement data table and an environmental data table, and store the processed settlement data and environmental data in a database. The settlement data table records the monitoring point ID, collection time, and settlement height information; the environmental data table records the collection time, temperature, and humidity information.

[0016] In a preferred embodiment, in step 102, the sedimentation data and environmental data stored in the database are analyzed to calculate the sedimentation rate and trend. The specific steps are as follows:

[0017] Step B1, merging data sets: extracting newly stored settlement data and environmental data from the database, merging the settlement data with the environmental data, and connecting them using the acquisition time as the key field to form a new data set D = {ID, T, H, Te, Hμ}, where ID represents the monitoring point ID, T is the acquisition time, which exists in both the settlement data and the environmental data, H is the settlement height information, Te is the temperature, and Hμ is the humidity;

[0018] Step B2, calculating the sedimentation rate: for each monitoring point i, calculate the sedimentation rate in each time period to form a sedimentation rate time series. The sedimentation rate refers to the rate of change of the sedimentation height per unit time. The specific calculation formula is as follows:

[0019]

[0020] in, represents the settlement height at time T1, is the settlement height at time T2, Δh i is the sedimentation rate of monitoring point i;

[0021] The sedimentation rate time series is in, Indicates the time T corresponding to the monitoring point i m The sedimentation rate;

[0022] Step B2, analysis of settlement trend: Use linear regression model to analyze settlement trend, and establish a linear regression model for the relationship between settlement height H and time t: H i (t) = α + βt + ε, and the model parameters α and β are obtained by least squares fitting, where β is the sedimentation change rate and ε is the error term.

[0023] In a preferred embodiment, in step 103, a settlement prediction model is constructed based on the settlement data and analysis results, and a settlement warning threshold is set based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered. The specific steps are as follows:

[0024] Step C1: Introduce the temperature and humidity in the environmental data into the settlement trend analysis, and establish a prediction model for the settlement data and environmental data: i (T)=β0+β1T+β2Te+β3Hμ+ε1, where H i (T) represents the predicted settlement height of monitoring point i at time T, β0 is the intercept of the model, (β1, β2, β3) are the regression coefficients of time T, temperature Te and humidity Hμ respectively, and ε1 is the error term;

[0025] Step C2, model training: divide the data set D = {ID, T, H, Te, Hμ} into a training set and a validation set, use the training set data to fit the established prediction model, and use the least squares method to minimize the sum of squared errors between the predicted value and the actual value. The specific calculation formula is as follows:

[0026]

[0027] Among them, S(λ) represents the loss function, H i actual (T) represents the actual settlement height of monitoring point i at time T, n represents the total number of samples of all monitoring points in the training set, λ0 is the intercept term of the model, (λ1, λ2, λ3) are the regression coefficients related to time, temperature and humidity respectively, Te iis the temperature of monitoring point i at time T, Hμ i is the humidity at monitoring point i at time T;

[0028] Step C3, model evaluation: Use the coefficient of determination and root mean square error to evaluate the fitting effect of the model. According to the evaluation results, adjust the model parameters (λ0, λ1, λ2, λ3). The specific calculation formula is as follows:

[0029]

[0030] Among them, R 2 is the coefficient of determination, RMSE is the root mean square error, represents the actual settlement height of monitoring point i at time T, is the mean of the actual settlement height, and n represents the total number of samples of all monitoring points in the training set;

[0031] Step C4, set dynamic settlement warning threshold: use the settlement height prediction value and environmental data output by the model, combine historical settlement data and error distribution, combine the changes in temperature and humidity with the predicted results of settlement data through weighting factors, and set a comprehensive dynamic warning threshold as Among them, H i (T) represents the predicted settlement height of monitoring point i at time T, Te is the temperature, Hμ is the humidity, It is a weighting coefficient, which indicates the influence of temperature, humidity and predicted settlement value on the threshold. When the settlement height exceeds the threshold, an alarm is triggered.

[0032] In a preferred embodiment, in step 104, according to the settlement warning threshold calculation method of step 103, it is checked whether the settlement height of each monitoring point exceeds the warning threshold, the monitoring point that triggers the warning is marked as an abnormal settlement area, and a monitoring report is generated. The specific steps are as follows:

[0033] Step D1, abnormality identification and location: compare the current settlement height of each monitoring point with the warning threshold of the point to determine whether it exceeds the set threshold. When the settlement height exceeds the warning threshold, mark the monitoring point as a settlement abnormal area, and calculate the percentage of actual settlement exceeding the threshold as an indicator of the severity of the abnormality; when the settlement height does not exceed the warning threshold, continue monitoring and do not mark it as an abnormality;

[0034] The specific calculation formula for the severity of the abnormality is as follows:

[0035]

[0036] Among them, Y(i,T) is the severity of the abnormality, is the actual settlement height of monitoring point i at time T, T threshold(i,T) is the warning threshold of monitoring point i at time T;

[0037] Step D2, generate anomaly detection report: for each monitoring point marked as abnormal settlement, save the monitoring point number, actual settlement value, warning threshold, timestamp and abnormal severity information, and generate a settlement abnormality detection report, including a list of abnormal monitoring points, abnormal time window, settlement exceeding standard analysis, environmental data and response suggestions; the abnormal monitoring point list lists all monitoring points that trigger alarms, including the number of each monitoring point, actual settlement height, warning threshold, and abnormal severity; the abnormal time window indicates the occurrence time and duration of the abnormality; the settlement exceeding standard analysis is to analyze the degree of settlement exceeding the threshold for each abnormal monitoring point, the environmental data is to provide the temperature and humidity at that time, and the response suggestion is that when the abnormal severity Y(i,T)≥50%, immediately stop work and carry out structural reinforcement; when the abnormal severity Y(i,T)<50%, continue monitoring and update data every hour.

[0038] The beneficial effects of the present invention are as follows: using high-precision equipment including GPS equipment, laser rangefinder, and environmental sensor to collect settlement data and environmental data in the settlement area, and recording the timestamp, monitoring point number, temperature, and humidity information of the data; preprocessing the settlement data and environmental data collected in the settlement area, and storing the processed data in a database; extracting the newly stored settlement data and environmental data from the database, and merging the settlement data with the environmental data to form a new data set; for each monitoring point, calculating the settlement rate in each time period to form a settlement rate time series, and performing trend analysis; constructing a settlement prediction model based on the settlement data and analysis results, and setting a settlement warning threshold based on the prediction results; when the monitoring data exceeds the warning threshold, triggering an alarm, checking whether the settlement height of each monitoring point exceeds the warning threshold, marking the monitoring point that triggers the warning as an abnormal settlement area, and generating a monitoring report; through the dynamic environmental observation method, it is possible to achieve real-time monitoring of ground settlement and effectively capture settlement changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0041] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0042] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. In order to enable any technician in the field to implement and use the present invention, the following description is given. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details that make the description of the present invention obscure. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0043] Example 1

[0044] This embodiment provides Figure 1 A dynamic environmental settlement observation method is shown, which specifically includes the following steps:

[0045] Step 101: Collect settlement data and environmental data of the settlement area, perform preprocessing, and store the processed data in a database;

[0046] Step 102, analyzing the settlement data and environmental data stored in the database to calculate the settlement rate and trend;

[0047] Step 103: construct a settlement prediction model based on the settlement data and analysis results, and set a settlement warning threshold based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered;

[0048] Step 104: According to the settlement warning threshold calculation method of step 103, check whether the settlement height of each monitoring point exceeds the warning threshold, mark the monitoring point that triggers the warning as an abnormal settlement area, and generate a monitoring report.

[0049] Preferably, in step 101, the settlement data and environmental data of the settlement area are collected and preprocessed, and the processed data is stored in a database to achieve real-time monitoring of the settlement data, and through the database query interface, it is convenient to extract and analyze the data in time. The specific steps are as follows:

[0050] Step A1, data collection: using high-precision equipment including GPS equipment, laser rangefinder, environmental sensor to collect settlement data and environmental data in the settlement area, and record the timestamp, monitoring point number, temperature, humidity information of the data, further including the following steps:

[0051] Step A101: determine the land subsidence area to be monitored, construct an electronic map of the area, and mark key infrastructure, terrain features and monitoring point locations. Divide the monitoring area into multiple sub-areas on the electronic map to facilitate management and data processing;

[0052] Step A102: reasonably arrange settlement monitoring points in each sub-area to ensure that key locations in each area are covered, and install settlement monitoring equipment at the monitoring points to monitor ground height changes in real time;

[0053] Step A103, setting the frequency and time interval of data collection to collect settlement data and environmental data once every hour, including settlement height, timestamp, monitoring point number, temperature and humidity information;

[0054] Step A2, preprocessing: perform a preliminary check on the collected raw data, identify and remove obvious outliers and erroneous data, use interpolation to complete the missing data to maintain data continuity, create a settlement data table and an environmental data table, and store the processed settlement data and environmental data in a database. The settlement data table records the monitoring point ID, collection time, and settlement height information; the environmental data table records the collection time, temperature, and humidity information.

[0055] Preferably, in step 102, the settlement data and environmental data stored in the database are analyzed to calculate the settlement rate and trend, so as to quantify the impact of settlement on the building structure and foundation stability. The specific steps are as follows:

[0056] Step B1, merging data sets: extracting newly stored settlement data and environmental data from the database, merging the settlement data with the environmental data, and connecting them using the acquisition time as the key field to form a new data set D = {ID, T, H, Te, Hμ}, where ID represents the monitoring point ID, T is the acquisition time, which exists in both the settlement data and the environmental data, H is the settlement height information, Te is the temperature, and Hμ is the humidity;

[0057] Step B2, calculating the sedimentation rate: for each monitoring point i, calculate the sedimentation rate in each time period to form a sedimentation rate time series. The sedimentation rate refers to the rate of change of the sedimentation height per unit time. The specific calculation formula is as follows:

[0058]

[0059] in, represents the settlement height at time T1, is the settlement height at time T2, Δh i is the sedimentation rate of monitoring point i, the unit is height / time;

[0060] The sedimentation rate time series is in, Indicates the time T corresponding to the monitoring point i m The sedimentation rate;

[0061] Step B2, analysis of settlement trend: Use linear regression model to analyze settlement trend, and establish a linear regression model for the relationship between settlement height H and time t: H i (t) = α + βt + ε, and the model parameters α and β are obtained by least squares fitting, where β is the sedimentation change rate and ε is the error term.

[0062] Preferably, in step 103, a settlement prediction model is constructed according to the settlement data and the analysis results, and a settlement warning threshold is set based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered to improve the pertinence and accuracy of monitoring. The specific steps are as follows:

[0063] Step C1: Introduce the temperature and humidity in the environmental data into the settlement trend analysis, and establish a prediction model for the settlement data and environmental data: i (T)=β0+β1T+β2Te+β3Hμ+ε1, where H i (T) represents the predicted settlement height of monitoring point i at time T, β0 is the intercept of the model, (β1, β2, β3) are the regression coefficients of time T, temperature Te and humidity Hμ respectively, and ε1 is the error term;

[0064] Step C2, model training: divide the data set D = {ID, T, H, Te, Hμ} into a training set and a validation set, use the training set data to fit the established prediction model, and use the least squares method to minimize the sum of squared errors between the predicted value and the actual value. The specific calculation formula is as follows:

[0065]

[0066] Among them, S(λ) represents the loss function, represents the actual settlement height of monitoring point i at time T, n represents the total number of samples of all monitoring points in the training set, λ0 is the intercept term of the model, (λ1, λ2, λ3) are the regression coefficients related to time, temperature and humidity respectively, Te i is the temperature of monitoring point i at time T, Hμ i is the humidity at monitoring point i at time T;

[0067] Step C3, model evaluation: Use the coefficient of determination and root mean square error to evaluate the fitting effect of the model. According to the evaluation results, adjust the model parameters (λ0, λ1, λ2, λ3). The specific calculation formula is as follows:

[0068]

[0069] Among them, R 2 It is the coefficient of determination, which measures the degree of fit of the model to the observed data. Its value range is between 0 and 1. The closer it is to 1, the better the fit of the model. RMSE is the root mean square error, which is used to measure the deviation between the predicted value and the actual value. represents the actual settlement height of monitoring point i at time T, is the mean of the actual settlement height, and n represents the total number of samples of all monitoring points in the training set;

[0070] Step C4, set dynamic settlement warning threshold: use the settlement height prediction value and environmental data output by the model, combine historical settlement data and error distribution, combine the changes in temperature and humidity with the predicted results of settlement data through weighting factors, and set a comprehensive dynamic warning threshold as Among them, H i (T) represents the predicted settlement height of monitoring point i at time T, Te is the temperature, Hμ is the humidity, It is a weighting coefficient, which indicates the influence of temperature, humidity and predicted settlement value on the threshold. When the settlement height exceeds the threshold, an alarm is triggered.

[0071] Preferably, in step 104, according to the settlement warning threshold calculation method of step 103, check whether the settlement height of each monitoring point exceeds the warning threshold, mark the monitoring point that triggers the warning as an abnormal settlement area, and generate a monitoring report, which helps to reduce the probability of accidents and avoid building tilt caused by abnormal settlement. The specific steps are as follows:

[0072] Step D1, abnormality identification and location: compare the current settlement height of each monitoring point with the warning threshold of the point to determine whether it exceeds the set threshold. When the settlement height exceeds the warning threshold, mark the monitoring point as a settlement abnormal area, and calculate the percentage of actual settlement exceeding the threshold as an indicator of the severity of the abnormality; when the settlement height does not exceed the warning threshold, continue monitoring and do not mark it as an abnormality;

[0073] The specific calculation formula for the severity of the abnormality is as follows:

[0074]

[0075] Among them, Y(i,T) is the severity of the abnormality, is the actual settlement height of monitoring point i at time T, T threshold (i,T) is the warning threshold of monitoring point i at time T;

[0076] Step D2, generate anomaly detection report: for each monitoring point marked as abnormal settlement, save the monitoring point number, actual settlement value, warning threshold, timestamp and abnormal severity information, and generate a settlement abnormality detection report, including a list of abnormal monitoring points, abnormal time window, settlement exceeding standard analysis, environmental data and response suggestions; the abnormal monitoring point list lists all monitoring points that trigger alarms, including the number of each monitoring point, actual settlement height, warning threshold, and abnormal severity; the abnormal time window indicates the occurrence time and duration of the abnormality; the settlement exceeding standard analysis is to analyze the degree of settlement exceeding the threshold for each abnormal monitoring point, the environmental data is to provide the temperature and humidity at that time, and the response suggestion is that when the abnormal severity Y(i,T)≥50%, immediately stop work and carry out structural reinforcement; when the abnormal severity Y(i,T)<50%, continue monitoring and update data every hour.

[0077] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A dynamic environmental settlement observation method, characterized in that: The specific steps include: Step 101: Collect settlement data and environmental data of the settlement area, perform preprocessing, and store the processed data in a database; Step 102, analyzing the settlement data and environmental data stored in the database to calculate the settlement rate and trend; Step 103: construct a settlement prediction model based on the settlement data and analysis results, and set a settlement warning threshold based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered; Step 104: According to the settlement warning threshold calculation method of step 103, check whether the settlement height of each monitoring point exceeds the warning threshold, mark the monitoring point that triggers the warning as an abnormal settlement area, and generate a monitoring report.

2. A dynamic environmental settlement observation method according to claim 1, characterized in that: In step 101, the settlement data and environmental data of the settlement area are collected and preprocessed, and the processed data are stored in a database. The specific steps are as follows: Step A1, data collection: Use high-precision equipment to collect settlement data and environmental data in the settlement area, and record the timestamp, monitoring point number, temperature, and humidity information of the data; Step A2, preprocessing: perform a preliminary check on the collected raw data, identify and remove outliers and erroneous data, use interpolation to complete the missing data to maintain data continuity, create a settlement data table and an environmental data table, and store the processed settlement data and environmental data in a database. The settlement data table records the monitoring point ID, collection time, and settlement height information; the environmental data table records the collection time, temperature, and humidity information.

3. A dynamic environmental settlement observation method according to claim 2, characterized in that: In the data collection of step A1, high-precision equipment including GPS equipment, laser rangefinder, and environmental sensor are used to collect settlement data and environmental data in the settlement area, and the timestamp, monitoring point number, temperature, and humidity information of the data are recorded, further comprising the following steps: Step A101: determine the land subsidence area to be monitored, construct an electronic map of the area, mark key infrastructure, terrain features and monitoring point locations, and divide the monitoring area into multiple sub-areas on the electronic map; Step A102: deploying settlement monitoring points in each sub-area and installing settlement monitoring equipment at the monitoring points to monitor the change of ground height in real time; Step A103, set the frequency and time interval of data collection to collect settlement data and environmental data once every hour, including settlement height, timestamp, monitoring point number, temperature and humidity information.

4. A dynamic environmental settlement observation method according to claim 1, characterized in that: In step 102, the settlement data and environmental data stored in the database are analyzed to calculate the settlement rate and trend. The specific steps are as follows: Step B1, merging data sets: extracting newly stored settlement data and environmental data from the database, merging the settlement data with the environmental data, and connecting them using the acquisition time as the key field to form a new data set D = {ID, T, H, Te, Hμ}, where ID represents the monitoring point ID, T is the acquisition time, which exists in both the settlement data and the environmental data, H is the settlement height information, Te is the temperature, and Hμ is the humidity; Step B2, calculate the sedimentation rate: for each monitoring point i, calculate the sedimentation rate in each time period to form a sedimentation rate time series. The specific calculation formula is as follows: in, represents the settlement height at time T1, is the settlement height at time T2, Δh i is the sedimentation rate of monitoring point i; Step B2, analysis of settlement trend: Use linear regression model to analyze settlement trend, and establish a linear regression model for the relationship between settlement height H and time t: H i (t) = α + βt + ε, and the model parameters α and β are obtained by least squares fitting, where β is the sedimentation change rate and ε is the error term.

5. A dynamic environmental settlement observation method according to claim 4, characterized in that: In step B2, the sedimentation rate time series is: in, Indicates the time T corresponding to the monitoring point i m sedimentation rate.

6. A dynamic environmental settlement observation method according to claim 1, characterized in that: In step 103, a settlement prediction model is constructed based on the settlement data and analysis results, and a settlement warning threshold is set based on the prediction results. When the monitoring data exceeds the warning threshold, an alarm is triggered. The specific steps are as follows: Step C1: Introduce the temperature and humidity in the environmental data into the settlement trend analysis, and establish a prediction model for the settlement data and environmental data: i (T)=β0+β1T+β2Te+β3Hμ+ε1, where H i (T) represents the predicted settlement height of monitoring point i at time T, β0 is the intercept of the model, (β1, β2, β3) are the regression coefficients of time T, temperature Te and humidity Hμ respectively, and ε1 is the error term; Step C2, model training: divide the data set D = {ID, T, H, Te, Hμ} into a training set and a validation set, use the training set data to fit the established prediction model, and use the least squares method to minimize the sum of squared errors between the predicted value and the actual value. The specific calculation formula is as follows: Among them, S(λ) represents the loss function, represents the actual settlement height of monitoring point i at time T, n represents the total number of samples of all monitoring points in the training set, λ0 is the intercept term of the model, (λ1, λ2, λ3) are the regression coefficients related to time, temperature and humidity respectively, Te i is the temperature of monitoring point i at time T, Hμ i is the humidity of monitoring point i at time T.

7. A dynamic environmental settlement observation method according to claim 6, characterized in that: The step 103 further includes the following steps: Step C3, model evaluation: Use the coefficient of determination and root mean square error to evaluate the model fitting effect. According to the evaluation results, adjust the model parameters (λ0, λ1, λ2, λ3). The specific calculation formula is as follows: Among them, R 2 is the coefficient of determination, RMSE is the root mean square error, represents the actual settlement height of monitoring point i at time T, is the mean of the actual settlement height, and n represents the total number of samples of all monitoring points in the training set; Step C4, setting dynamic settlement warning threshold: using the settlement height prediction value and environmental data output by the model, combined with historical settlement data and error distribution, the changes in temperature and humidity are combined with the predicted results of settlement data through weighting factors, and a comprehensive dynamic warning threshold is set as Among them, H i (T) represents the predicted settlement height of monitoring point i at time T, Te is the temperature, Hμ is the humidity, It is a weighting coefficient. When the monitored settlement height exceeds the threshold, an alarm is triggered.

8. A dynamic environmental settlement observation method according to claim 1, characterized in that: In step 104, according to the settlement warning threshold calculation method of step 103, check whether the settlement height of each monitoring point exceeds the warning threshold, mark the monitoring point that triggers the warning as a settlement abnormal area, and generate a monitoring report. The specific steps are as follows: Step D1, abnormality identification and location: compare the current settlement height of each monitoring point with the warning threshold of the point to determine whether it exceeds the set threshold. When the settlement height exceeds the warning threshold, mark the monitoring point as a settlement abnormal area, and calculate the percentage of actual settlement exceeding the threshold as an indicator of the severity of the abnormality; when the settlement height does not exceed the warning threshold, continue monitoring and do not mark it as an abnormality; The specific calculation formula for the severity of the abnormality is as follows: Among them, Y(i,T) is the severity of the abnormality, is the actual settlement height of monitoring point i at time T, T threshold (i,T) is the warning threshold of monitoring point i at time T; Step D2, generate anomaly detection report: for each monitoring point marked as abnormal settlement, save the monitoring point number, actual settlement value, warning threshold, timestamp and abnormal severity information, and generate a settlement abnormality detection report, including a list of abnormal monitoring points, abnormal time window, settlement excess analysis, environmental data and response suggestions; the abnormal monitoring point list lists all monitoring points that trigger alarms, including the number of each monitoring point, actual settlement height, warning threshold, and abnormal severity; the abnormal time window indicates the occurrence time and duration of the abnormality; the settlement excess analysis is to analyze the degree to which the settlement exceeds the threshold for each abnormal monitoring point, and the environmental data provides the temperature and humidity at that time, The response recommendation is to immediately stop construction and carry out structural reinforcement when the severity of the abnormality Y(i,T) ≥ 50%. When the abnormal severity Y(i,T) is less than 50%, continue monitoring and update the data every hour.

Images