Section abnormity judgment method based on settlement observation

Abstract

The invention relates to the technical field of railway surveying and mapping, and provides a section anomaly judgment method based on settlement observation, which comprises the following steps: acquiring section surveying and mapping requirements of settlement observation and settlement observation terminal equipment information, matching equipment parameters, performing state detection, then analyzing the surveying and mapping requirements, generating coordinate information of a to-be-observed point, and judging whether the to-be-observed point is abnormal or not. Establishing a database to store related data, utilizing the database and historical data to construct a section settlement observation point prediction model, outputting a settlement prediction result, comparing the settlement prediction result with a preset abnormity reminding threshold value, if the prediction result is abnormal, obtaining real-time settlement observation section data, comparing the real-time settlement observation section data, and optimizing the prediction model until the prediction model accords with an error range. According to the method, automatic reminding and level-to-level management of abnormal settlement or upheaval are achieved, safe operation of railway engineering is achieved, the accuracy of settlement observation data is effectively improved, section abnormal data can be found in advance, and powerful support is provided for maintenance of the railway engineering.

Description

Technical Field

[0001] The invention relates to the technical field of railway surveying and mapping, and in particular to a method for judging section anomaly based on settlement observation. Background Art

[0002] With the continuous advancement of railway engineering technology, settlement and deformation observation technology is also developing day by day. At present, a lot of research has been carried out at home and abroad on railway subgrade settlement observation, and a variety of observation methods and technical means have been formed. Automated monitoring technology, non-contact monitoring methods of remote sensing technology, etc. have been widely used. The development of technology has provided strong support for the safety and stability assessment of railway engineering. In particular, the emergence of section settlement and uplift abnormality judgment technology has made it more accurate and timely to capture subtle changes in railway engineering.

[0003] In railway engineering, the abnormal judgment technology of cross-section settlement and uplift is to set up observation points at key locations and collect data regularly to analyze the changes in settlement and uplift. Specifically, this technology uses precision measuring instruments, such as levels and cross-sectioners, to regularly observe the railway roadbed. The observation data will be sorted and analyzed in a timely manner to detect any settlement or uplift trends. When the data is abnormal, such as the settlement rate exceeds the preset threshold, the system will immediately issue a reminder so that engineering personnel can check in time and take appropriate remedial measures.

[0004] Although the section settlement and uplift abnormality judgment technology plays a role in railway engineering, there are still the following technical pain points. The observation process is interfered by various factors, which affects the accuracy of the observation data. The settlement observation has high requirements for the accuracy and real-time performance of the data, which to a certain extent increases the difficulty and cost of the technology application. Therefore, it is necessary to judge the abnormal data of the section when conducting settlement observation, discover the errors in the observation data in advance, and improve the accuracy of the settlement observation. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for judging cross-section anomalies based on settlement observations to solve the problem that the observation process is interfered by various factors, which affects the accuracy of the observation data. When conducting settlement observations, the abnormal data of the cross-section must be judged to discover errors in advance.

[0006] The present invention provides a method for determining section anomaly based on settlement observation, comprising:

[0007] Step S101, obtaining the cross-sectional surveying and mapping requirements of settlement observation and the settlement observation terminal equipment information, matching the settlement observation terminal equipment parameters in a preset settlement observation knowledge base according to the cross-sectional surveying and mapping requirements of the settlement observation, obtaining the equipment parameters corresponding to the settlement observation terminal equipment, loading the equipment parameters corresponding to the settlement observation terminal equipment into the settlement observation terminal equipment, performing an operation status detection on the settlement observation terminal equipment, and obtaining the operation status detection result of the settlement observation terminal equipment;

[0008] The detection result of the operation status of the settlement observation terminal equipment includes the equipment information of the settlement observation terminal operating normally and the equipment information of the settlement observation terminal operating abnormally, and the surveying and mapping equipment corresponding to the equipment information of the settlement observation terminal operating normally is used as the surveying and mapping equipment executable by the surveying and mapping task;

[0009] Step S102, parsing the cross-section surveying and mapping requirements of the settlement observation, obtaining cross-section settlement observation task information, surveying and mapping equipment terminal requirement information, and surveying and mapping parameter requirement information, wherein the surveying and mapping parameter requirement information includes a cross-section abnormality reminder threshold and a settlement observation terminal equipment operation abnormality reminder threshold, and the cross-section settlement observation task information includes cross-section position information, deformation rate surveying and mapping tasks, and total deformation surveying and mapping tasks, substituting the cross-section settlement observation task information into a preset cross-section surveying and mapping point model of the settlement observation, and generating cross-section points to be observed for the settlement observation;

[0010] Step S103, establishing a database for data storage, retrieving the control point coordinate data of the corresponding position area in the database according to the section position information, performing coordinate matching on the section observation point to be observed based on the control point coordinate data, obtaining the coordinate information of the point to be observed, retrieving the corresponding section settlement observation history data in the database according to the coordinate information of the point to be observed, obtaining the settlement observation history data of the coordinate surface of the point to be observed, the settlement observation history data of the coordinate surface of the point to be observed including the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold, and constructing a section settlement observation point prediction model through the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold;

[0011] Step S104, substituting the coordinate information of the point to be observed into the cross-section settlement observation point prediction model, outputting the settlement prediction result of the point to be observed, using the cross-section abnormality reminder threshold in the surveying and mapping parameter requirement information to compare data with the settlement prediction result of the point to be observed, and if the settlement prediction result of the point to be observed is within the cross-section abnormality reminder threshold in the surveying and mapping parameter requirement information, generating first cross-section abnormality warning information;

[0012] If the settlement prediction result of the observation point is not within the section abnormality warning threshold range in the surveying and mapping parameter requirement information, then the real-time settlement observation section data collected by the surveying and mapping task executable surveying and mapping equipment is obtained, and the real-time settlement observation section data is substituted into the preset settlement observation point analysis model to obtain the real-time deformation rate and the real-time total deformation of the settlement observation point, and then step 105 is executed;

[0013] Step S105, comparing the real-time deformation rate and the real-time total deformation of the settlement observation point with the settlement prediction result of the point to be observed, and obtaining the error value between the prediction and the actual observation of the point to be observed; if the error value between the prediction and the actual observation of the point to be observed is greater than the prediction error range, optimizing the cross-section settlement observation point prediction model and the settlement observation point analysis model to obtain an optimized cross-section settlement observation point prediction model and an optimized settlement observation point analysis model; using the optimized cross-section settlement observation point prediction model to perform data processing on the coordinate information of the point to be observed, and obtaining an optimized settlement prediction result of the point to be observed; using the optimized settlement observation point analysis model to perform data processing on the real-time settlement observation section data, and obtaining an optimized real-time deformation rate and a real-time total deformation of the settlement observation point;

[0014] Step 106, comparing the optimized settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the comparison result of the settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point meets the preset error range, then using the section abnormality reminder threshold in the surveying and mapping parameter requirement information to compare data with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point are within the section abnormality reminder threshold range in the surveying and mapping parameter requirement information, then generating second section abnormality warning information;

[0015] If the comparison result of the optimized settlement prediction result of the point to be observed and the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point do not meet the preset error range, the real-time settlement observation section data is substituted into the optimized section settlement observation point prediction model to obtain the real-time section settlement observation point prediction result, and the real-time section settlement observation point prediction result is compared with the settlement prediction result of the point to be observed. If the real-time section settlement observation point prediction result is inconsistent with the settlement prediction result of the point to be observed, a data accuracy detection process is performed;

[0016] The data accuracy detection process includes performing an accuracy detection on the optimized cross-section settlement observation point prediction model. If the accuracy detection of the optimized cross-section settlement observation point prediction model is qualified, then performing an accuracy group detection on the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task. If there is abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then generating data collection error warning information. If there is no abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then optimizing the settlement observation point analysis model, using the optimized settlement observation point analysis model to analyze the real-time settlement observation cross-section data, setting the number of detection times of the data accuracy detection process and the expected cross-section settlement observation accuracy value of the data accuracy detection, when the data accuracy detection process reaches the number of detection times or reaches the expected cross-section settlement observation accuracy value, the data accuracy detection process stops.

[0017] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S101 comprises:

[0018] Step S1011, obtaining an identifier of the settlement observation terminal device, the identifier including a device ID and a serial number, searching for device parameters corresponding to the settlement observation terminal device in a pre-built knowledge base according to the identifier of the settlement observation terminal device, the device parameters including the accuracy of the device, the measurement range of the device, the calibration period of the device, and the working environment of the device;

[0019] Step S1012, loading the device parameters corresponding to the settlement observation terminal device found in the preset settlement observation knowledge base into the information management system of the settlement observation terminal device, starting the self-check program of the settlement observation terminal device, checking whether the functions of the settlement observation terminal device are normal, and checking whether the functions of the settlement observation terminal device include whether the sensor is working, whether the data transmission status is normal, and whether the power status of the settlement observation terminal device is normal;

[0020] Step S1013, by comparing with the preset normal operating status parameters of the settlement observation terminal equipment, analyzing the current operating status of the settlement observation terminal equipment, real-time monitoring and analysis of the output data of the settlement observation terminal equipment, and obtaining the result of the operating status detection, the analysis of the output data of the settlement observation terminal equipment includes: detecting whether there is abnormal fluctuation in the output data of the settlement observation terminal equipment, and monitoring whether the output data of the settlement observation terminal equipment deviates from the normal range.

[0021] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S101 comprises:

[0022] Step S1014, generating an operation status report of the settlement observation terminal device according to the result of the operation status detection, wherein the operation status report of the settlement observation terminal device includes the detection index of the device and the function completion status of the device;

[0023] Step S1015, storing the operation status report of the settlement observation terminal device in the information management system, and classifying and marking the device according to the operation status report of the settlement observation terminal device, wherein the device classification mark includes normal operation and abnormal operation;

[0024] Step S1016: Stop using the device that is marked as abnormally operating.

[0025] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S102 comprises:

[0026] Step S1021, determining the observation target, wherein the observation target includes the observed section position, section range and purpose of the observed section, wherein the purpose of the observed section includes evaluating the railway subgrade stability, railway bridge foundation settlement and railway foundation deformation;

[0027] Step S1022, acquiring engineering data according to the observed section position, the section range and the purpose of the observed section, and determining the geological conditions of the section area, the structural form of the section area and the deformation characteristics of the section area according to the engineering data, wherein the engineering data includes engineering design drawings, geological survey reports and construction plans, the geological conditions of the section area include stratum distribution, soil layer properties and groundwater level, and the structural form of the section area includes the pile foundation arrangement of the railway bridge and the load-bearing structure of the railway.

[0028] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S102 comprises:

[0029] Step S1023, determining the type of observation points for section layout, wherein the types of observation points for section layout include four corners, large corners, 10-15 meter areas along the rails, both sides of settlement joints or expansion joints, new and old rails or high and low rails, and intersections of vertical and horizontal rails;

[0030] Step S1024, constructing a cross-section surveying and mapping point model for settlement observation according to the cross-section layout observation point type, the output content of the cross-section surveying and mapping point model for settlement observation includes the position, number and deformation characteristics of each observation point.

[0031] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S103 comprises:

[0032] Step S1031, obtaining a geological survey report, climate condition data, structural characteristic data, and historical observation data of the area where the section is located, wherein the geological survey report includes stratum distribution, soil layer properties, groundwater level, and geological conditions;

[0033] The climate condition data includes meteorological data of the area, which includes rainfall, temperature, humidity and wind speed; the structural characteristic data includes the structural form, material properties and load conditions of the section; the historical observation data includes the control point coordinate data of the section settlement observation history data of the area, previous observation results and abnormal warning threshold.

[0034] Furthermore, in the cross-section anomaly determination method based on settlement observation of the present invention, the step S103 further includes:

[0035] Step S1032, obtaining the influencing factors of historical cross-section settlement observation, wherein the influencing factors of historical cross-section settlement observation include the influence of geological conditions on settlement rate and deformation mode, the influence of climate conditions on soil moisture, and the influence of temperature stress;

[0036] Step S1033, according to the historical cross-section settlement observation influencing factor results, a preliminary abnormality alert threshold range is set, and the preliminary abnormality alert threshold range is used as the real-time abnormality alert threshold range.

[0037] Furthermore, in the cross-section anomaly determination method based on settlement observation described in the present invention, step S105 comprises:

[0038] Step S1051, determining the basis for data grouping according to the cross-section mapping requirements of the settlement observation and the settlement observation terminal equipment information, the basis for data grouping including time, location and geological conditions;

[0039] Step S1052, grouping the real-time settlement observation section data according to the data grouping basis, wherein the real-time settlement observation section data grouping includes dividing the data into different time periods according to the observation time, and dividing the data into different sections or measuring points according to the location;

[0040] Step S1053, perform quality inspection on each group of data in the grouped real-time settlement observation section data, check the continuity, stability and outliers of each group of data, obtain the historical data and design standards corresponding to each group of data, compare and analyze each group of data with the historical data and design standards, check whether each group of data has data points that exceed the allowable range of the design standards, treat the data points that exceed the allowable range of the design standards as outliers, and remove the detected outlier data.

[0041] Furthermore, the section abnormality judgment method based on settlement observation of the present invention further includes:

[0042] Receive and store the settlement observation data of each measuring point, wherein the settlement observation data of each measuring point includes the deformation rate and the total deformation. When it is detected that the deformation rate or the uplift rate of the total deformation exceeds the set dynamic threshold, the server will automatically trigger an abnormal settlement or abnormal uplift reminder;

[0043] The server will automatically trigger abnormal subsidence or abnormal uplift reminders via SMS and email to notify management personnel in real time.

[0044] Furthermore, the section abnormality judgment method based on settlement observation of the present invention further includes:

[0045] The server establishes reminder levels for multiple measuring points. For multiple measuring points in the same section, the server compares the reminder levels of multiple measuring points.

[0046] If the reminder levels of different measuring points in the same section are different, the server will select the highest level as the final reminder level of the section;

[0047] When the final alert level of the section is determined, the server will automatically generate alert information, including specific data of the anomaly, the determined alert level, and processing suggestions.

[0048] Beneficial effects of the present invention:

[0049] The present invention performs strict operation status detection on the terminal equipment before settlement observation, so that only equipment in good condition participates in the surveying and mapping task, thereby effectively avoiding the adverse effects of equipment failure or abnormality on the accuracy of observation data.

[0050] During the observation process, the present invention can timely discover and correct data deviations through real-time data comparison and model optimization technology, thereby further improving the accuracy of the observation data.

[0051] The present invention constructs an advanced cross-section settlement observation point prediction model, which can scientifically predict the settlement situation based on historical data and current observation conditions, significantly improving the ability to judge abnormal settlement. By setting reasonable cross-section abnormality reminder thresholds and settlement observation terminal equipment operation abnormality reminder thresholds, the present invention realizes real-time monitoring and early warning of abnormal situations, ensuring that potential settlement problems can be discovered and handled in a timely manner.

[0052] The present invention significantly improves the work efficiency of settlement observation and abnormal judgment by introducing automated and intelligent technical means, such as automatically triggering abnormal reminders and automatically optimizing prediction models, and greatly reduces the burden of manual operation. At the same time, by establishing an efficient database and model, the present invention realizes rapid storage, processing and analysis of data, further improving work efficiency.

[0053] The present invention provides a strong guarantee for the safe operation of railway projects by accurately acquiring settlement observation data and scientifically judging abnormal situations. It can timely discover and deal with potential settlement problems, effectively preventing railway accidents and losses caused by settlement. In addition, the present invention notifies managers of abnormal reminder information in real time, enabling managers to respond quickly and take necessary measures, further improving the safety of railway projects.

[0054] The implementation and application of the present invention promotes the progress and development of railway engineering settlement observation and abnormal judgment technology, introduces advanced automatic monitoring technology and model optimization method, and improves the accuracy and efficiency of settlement observation. At the same time, the method of the present invention can also provide reference and reference for other similar engineering fields.

[0055] In summary, the present invention has shown significant beneficial effects in improving the accuracy of observation data, enhancing the ability to judge abnormalities, improving work efficiency, ensuring the safety of railway projects, and promoting technological progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0057] Figure 1 A schematic diagram of the overall method flow provided by an embodiment of the present invention.

[0058] Figure 2 This is a schematic diagram of the step S101 flow chart provided in an embodiment of the present invention.

[0059] Figure 3 This is a schematic diagram of the step S102 flow chart provided in an embodiment of the present invention.

[0060] Figure 4 This is a schematic diagram of the process flow of step S103 provided in an embodiment of the present invention.

[0061] Figure 5 This is a schematic diagram of the process flow of step S105 provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0063] The present invention provides a method for determining section anomaly based on settlement observation, comprising:

[0064] Step S101, obtaining the cross-sectional surveying and mapping requirements of settlement observation and the settlement observation terminal equipment information, matching the settlement observation terminal equipment parameters in a preset settlement observation knowledge base according to the cross-sectional surveying and mapping requirements of the settlement observation, obtaining the equipment parameters corresponding to the settlement observation terminal equipment, loading the equipment parameters corresponding to the settlement observation terminal equipment into the settlement observation terminal equipment, performing an operation status detection on the settlement observation terminal equipment, and obtaining the operation status detection result of the settlement observation terminal equipment;

[0065] Obtain the cross-section surveying and mapping requirements for settlement observation, which include the location of the observed cross section and the frequency of observation;

[0066] The equipment information of the settlement observation terminal is obtained, including the equipment ID and serial number. The equipment ID and serial number are used to find the corresponding equipment parameters in the knowledge base.

[0067] Parameter matching in the preset settlement observation knowledge base: Based on the collected equipment information, search and match the corresponding equipment parameters in the knowledge base, covering the equipment's accuracy, measurement range, calibration cycle, and suitable working environment, etc.

[0068] Load the matching equipment parameters into the corresponding settlement observation equipment to ensure that the equipment can operate according to the correct parameters. Start the equipment's self-test program and comprehensively check the equipment's functional status, including the working condition of the sensor, the smoothness of data transmission, and the power status of the equipment.

[0069] By comparing with the preset normal operating status parameters, the current operating status of the equipment is analyzed and an operating status report is generated. The operating status report includes the distinction between equipment that is operating normally and equipment that is operating abnormally.

[0070] Based on the operation status detection results, the equipment that is operating normally is determined as the equipment that can perform the surveying and mapping task.

[0071] The detection result of the operation status of the settlement observation terminal equipment includes the equipment information of the settlement observation terminal operating normally and the equipment information of the settlement observation terminal operating abnormally, and the surveying and mapping equipment corresponding to the equipment information of the settlement observation terminal operating normally is used as the surveying and mapping equipment executable by the surveying and mapping task;

[0072] The results of the equipment operation status test of the settlement observation terminal mainly include two parts of information: the normal operation equipment information of the settlement observation terminal and the abnormal operation equipment information of the settlement observation terminal. Among them, "normal operation" means that the function and status of the equipment are normal and no abnormality is detected, while "abnormal operation" means that the equipment has abnormal function or status and may need further maintenance or replacement.

[0073] When processing these test results, we first obtain the operating status reports of all equipment, and classify and mark the equipment as "normal operation" or "abnormal operation" based on these reports. Then, we select the equipment marked as "normal operation" and use the equipment information as the executable equipment for the surveying and mapping task. This means that when actually conducting settlement observations, only equipment with normal functions and stable status will be selected, thereby improving the accuracy of the observation data.

[0074] Step S102, parsing the cross-section surveying and mapping requirements of the settlement observation, obtaining cross-section settlement observation task information, surveying and mapping equipment terminal requirement information, and surveying and mapping parameter requirement information, wherein the surveying and mapping parameter requirement information includes a cross-section abnormality reminder threshold and a settlement observation terminal equipment operation abnormality reminder threshold, and the cross-section settlement observation task information includes cross-section position information, deformation rate surveying and mapping tasks, and total deformation surveying and mapping tasks, substituting the cross-section settlement observation task information into a preset cross-section surveying and mapping point model of the settlement observation, and generating cross-section points to be observed for the settlement observation;

[0075] The purpose of analyzing the cross-section mapping requirements for settlement observation is to obtain specific task information and parameter requirements related to settlement observation and provide clear guidance for subsequent observation work.

[0076] Section location information specifically describes the geographical location of the section to be observed in the railway project, improving the accuracy of the observation work.

[0077] The deformation rate mapping task focuses on the changes in the deformation rate of the section over time, providing key data for evaluating the stability of the section.

[0078] The total deformation mapping task focuses on the total deformation accumulated in the section during the observation period, reflecting the overall deformation of the section.

[0079] Obtain terminal demand information for surveying and mapping equipment: clarify the specific equipment types and performance requirements required for settlement observation, and improve the applicability of observation equipment.

[0080] Section abnormality warning threshold: when the observed deformation rate or total deformation exceeds this value, the system will automatically issue an abnormality warning to promptly warn of potential safety issues.

[0081] The abnormal operation reminder threshold of the settlement observation terminal equipment is used to monitor the abnormal operation reminder threshold of the settlement observation terminal equipment to ensure the normal operation of the equipment and the reliability of the observation data.

[0082] The cross-section settlement observation task information obtained by analysis is substituted into the preset cross-section surveying and mapping point model of settlement observation.

[0083] The cross-section mapping point model for settlement observation is based on the input task information and intelligently outputs the specific points to be observed required for settlement observation, including the location, number and possible deformation characteristics of each observation point, providing a solid foundation for subsequent data collection and analysis.

[0084] Step S103, establishing a database for data storage, retrieving the control point coordinate data of the corresponding position area in the database according to the section position information, performing coordinate matching on the section observation point to be observed based on the control point coordinate data, obtaining the coordinate information of the point to be observed, retrieving the corresponding section settlement observation history data in the database according to the coordinate information of the point to be observed, obtaining the settlement observation history data of the coordinate surface of the point to be observed, the settlement observation history data of the coordinate surface of the point to be observed including the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold, constructing a section settlement observation point prediction model through the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold, substituting the coordinate information of the point to be observed into the section settlement observation point prediction model, outputting the settlement prediction result of the point to be observed, using the section abnormality reminder threshold in the surveying and mapping parameter requirement information and the settlement prediction result of the point to be observed for data comparison, if the settlement prediction result of the point to be observed is within the section abnormality reminder threshold range in the surveying and mapping parameter requirement information, then generating the first section abnormality warning information;

[0085] In order to effectively store and manage settlement observation related data, it is first necessary to establish a database for data storage.

[0086] Retrieve the coordinate data of the control points, and retrieve the coordinate data of the control points of the corresponding location area from the established database according to the cross-section location information. These control point coordinate data are the basis for subsequent coordinate matching and settlement prediction.

[0087] Coordinate matching, using the retrieved control point coordinate data, accurately matches the coordinates of the points to be observed in the section of the settlement observation, so as to obtain the specific coordinate information of the points to be observed.

[0088] Retrieve historical data, and further retrieve the corresponding section settlement observation historical data from the database according to the coordinate information of the point to be observed. The section settlement observation historical data not only includes the historical observation records, but also specifically includes the difference between the historical section abnormality warning threshold and the current section abnormality warning threshold, providing a basis for the subsequent prediction model construction.

[0089] Based on the difference between the historical section abnormality warning threshold and the current section abnormality warning threshold, a prediction model for section settlement observation points is constructed. This model can comprehensively consider historical observation data and current observation conditions to scientifically predict the settlement of the observation point.

[0090] The coordinate information of the observation point is substituted into the constructed cross-section settlement observation point prediction model, and the settlement prediction result of the observation point is output through the operation of the model.

[0091] The section abnormality warning threshold in the surveying and mapping parameter requirement information is compared with the settlement prediction result of the observation point. Through this comparison process, it can be determined whether the prediction result is within the preset abnormality warning threshold range, thereby evaluating whether the settlement of the section is normal.

[0092] If the settlement prediction result of the observation point is within the section abnormality warning threshold range in the surveying and mapping parameter requirement information, it means that the section may have settlement abnormality. At this time, the system will automatically generate the first section abnormality warning information to remind relevant personnel to pay attention to and deal with possible settlement problems in a timely manner.

[0093] Step S104, if the settlement prediction result of the point to be observed is not within the section abnormality reminder threshold range in the surveying and mapping parameter requirement information, then the real-time settlement observation section data collected by the surveying and mapping task executable surveying and mapping equipment is obtained, and the real-time settlement observation section data is substituted into the preset settlement observation point analysis model to obtain the real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point, and the real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point are compared with the settlement prediction result of the point to be observed to obtain the error value between the prediction and the actual observation of the point to be observed, and if the error value between the prediction and the actual observation of the point to be observed is greater than the prediction error range, the section settlement observation point prediction model and the settlement observation point analysis model are optimized to obtain the optimized section settlement observation point prediction model and the optimized settlement observation point analysis model, and the optimized section settlement observation point prediction model is used to perform data processing on the coordinate information of the point to be observed to obtain the optimized The settlement prediction result of the point to be observed is obtained by using the optimized settlement observation point analysis model to compare the real-time settlement observation section data to obtain the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point, and the settlement prediction result of the point to be observed is compared with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the comparison result of the settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point meets the preset error range, the section abnormality reminder threshold in the surveying and mapping parameter requirement information is used to compare the data with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the settlement prediction result of the point to be observed is within the section abnormality reminder threshold range of the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point in the surveying and mapping parameter requirement information, a second section abnormality warning information is generated;

[0094] Determine whether the settlement prediction result of the observation point is within the section abnormality warning threshold range in the surveying and mapping parameter requirement information. If it is not within the range, it means that the prediction result deviates greatly from the expectation and further processing is required in subsequent steps.

[0095] Acquiring surveying and mapping tasks can execute real-time settlement observation section data collected by surveying and mapping equipment. These data are real data reflecting the current settlement of the section, providing a basis for subsequent analysis and comparison.

[0096] Substitute the real-time settlement observation section data into the preset settlement observation point analysis model, and obtain the real-time deformation rate and real-time total deformation of the settlement observation point through the model operation. These data are indicators for evaluating the settlement of the section.

[0097] The calculated real-time deformation rate and real-time total deformation of the settlement observation point are compared with the settlement prediction results of the observation point to be observed, and the error value between the prediction and the actual observation is calculated. This error value reflects the accuracy and reliability of the prediction model.

[0098] If the error between the prediction and actual observation of the observation point is greater than the preset prediction error range, it means that there is a large deviation or deficiency in the prediction model, and the prediction model of the section settlement observation point and the analysis model of the settlement observation point need to be optimized.

[0099] The cross-section settlement observation point prediction model and settlement observation point analysis model are optimized to obtain the optimized model. The optimization process may include adjusting model parameters, improving model algorithms, etc. to improve the accuracy and prediction ability of the model.

[0100] The optimized cross-section settlement observation point prediction model is used to process the coordinate information of the observation points to obtain the optimized settlement prediction results of the observation points. At the same time, the optimized settlement observation point analysis model is used to process the real-time settlement observation section data to obtain the optimized settlement observation point real-time deformation rate and real-time total deformation.

[0101] The settlement prediction results of the optimized observation points are compared with the real-time deformation rate and real-time total deformation of the optimized settlement observation points. If the comparison results meet the preset error range, it means that the optimized model has high accuracy and reliability.

[0102] Finally, the section abnormality warning threshold in the surveying and mapping parameter requirement information is used to compare the data with the optimized real-time deformation rate and real-time total deformation of the settlement observation point. If the settlement prediction result of the optimized observation point and the optimized real-time deformation rate and real-time total deformation of the settlement observation point are within the section abnormality warning threshold range, it means that there may be settlement abnormality in the section. At this time, the second section abnormality warning information is generated to remind relevant personnel to pay attention to and deal with possible settlement problems in time.

[0103] Through these meticulous steps, step S104 achieves accurate judgment of the cross-section settlement and abnormal warning, providing strong guarantee for the safe operation of railway projects.

[0104] Step S105, if the comparison result of the optimized settlement prediction result of the point to be observed and the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point does not meet the preset error range, the real-time settlement observation section data is substituted into the optimized section settlement observation point prediction model to obtain the real-time section settlement observation point prediction result, and the real-time section settlement observation point prediction result is compared with the settlement prediction result of the point to be observed. If the real-time section settlement observation point prediction result is inconsistent with the settlement prediction result of the point to be observed, a data accuracy detection process is performed;

[0105] If the comparison results of the optimized settlement prediction results of the observation points and the optimized real-time deformation rate and real-time total deformation of the settlement observation points do not meet the preset error range, it means that there is a large deviation between the prediction results and the actual situation, and a series of follow-up operations are required.

[0106] The real-time settlement observation section data is substituted into the optimized section settlement observation point prediction model. Through the operation of the model, the real-time section settlement observation point prediction result is obtained. The real-time section settlement observation point prediction result reflects the predicted value of the current settlement situation of the section.

[0107] The prediction results of the real-time cross-section settlement observation points are compared with the settlement prediction results of the points to be observed. Through the comparison, the accuracy and reliability of the prediction model and the validity of the real-time observation data can be evaluated.

[0108] If the real-time cross-section settlement observation point prediction results are inconsistent with the settlement prediction results of the observation point, it means that there may be problems with the prediction model or real-time observation data, and the data accuracy detection process is triggered.

[0109] The optimized section settlement observation point prediction model was tested for accuracy to evaluate the model's prediction ability and stability.

[0110] If the model accuracy test is qualified, the data collected by the surveying and mapping equipment can be grouped for accuracy testing to further verify the reliability of the data.

[0111] If there is abnormal data in the detection, a data collection error warning message will be generated to remind relevant personnel to pay attention to and handle the data error in a timely manner.

[0112] If there is no abnormal data in the detection, the settlement observation point analysis model is optimized, and the optimized model is used to analyze the real-time settlement observation section data to improve the accuracy and reliability of the prediction.

[0113] Set the number of inspections for the data accuracy inspection process and the expected cross-sectional settlement observation accuracy value for the data accuracy inspection. Stop the inspection when the process reaches the number of inspections or the expected accuracy value.

[0114] The basis for data grouping is determined according to the cross-section mapping requirements of settlement observation and the settlement observation terminal equipment information, including time, location, and geological conditions.

[0115] The real-time settlement observation section data are grouped according to the data grouping basis so that each group of data can be independently quality tested.

[0116] Perform quality checks on each set of data in the grouping to check the continuity, stability, and outliers of the data to ensure the accuracy and reliability of the data.

[0117] During the data quality detection process, data points that exceed the allowable range of the design standards are removed as outliers to ensure the accuracy and validity of the data.

[0118] Step S105 realizes the comparison between the optimized model prediction results and the real-time observation data and the execution of the data accuracy detection process, which provides a strong guarantee for the safe operation of the railway project.

[0119] The data accuracy detection process includes performing an accuracy detection on the optimized cross-section settlement observation point prediction model. If the accuracy detection of the optimized cross-section settlement observation point prediction model is qualified, then performing an accuracy group detection on the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task. If there is abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then generating data collection error warning information. If there is no abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then optimizing the settlement observation point analysis model, using the optimized settlement observation point analysis model to analyze the real-time settlement observation cross-section data, setting the number of detection times of the data accuracy detection process and the expected cross-section settlement observation accuracy value of the data accuracy detection, when the data accuracy detection process reaches the number of detection times or reaches the expected cross-section settlement observation accuracy value, the data accuracy detection process stops.

[0120] The optimized cross-section settlement observation point prediction model accuracy test is carried out to improve the prediction ability of the model. If the model accuracy test is qualified, the next step of data grouping test is continued.

[0121] The surveying and mapping task can perform group detection of surveying and mapping equipment data accuracy, and perform group detection of the data collected by the surveying and mapping equipment to verify the reliability of the data. The group detection is based on factors such as time, location, and geological conditions to ensure the independence and representativeness of each group of data. If abnormal data is found in the data group detection, the system will automatically generate data collection error warning information to remind managers to pay attention to problems in the data.

[0122] If no abnormal data is found in the data grouping detection, the settlement observation point analysis model is optimized to improve the accuracy of the model's analysis of the real-time settlement observation section data. The optimized settlement observation point analysis model is used to analyze the real-time settlement observation section data to obtain a more accurate settlement situation.

[0123] Set the number of tests for the data accuracy test process and the expected cross-sectional settlement observation accuracy value for the data accuracy test to ensure the efficiency and effectiveness of the test process. When the data accuracy test process reaches the preset number of tests or reaches the expected cross-sectional settlement observation accuracy value, the test process stops to avoid unnecessary repeated tests.

[0124] When abnormal data is found in data group detection, the system will automatically generate data collection error warning information so that corrective measures can be taken in time. Managers should review and process the data based on the warning information to ensure the accuracy and reliability of the data.

[0125] The settlement observation point analysis model is optimized to improve the accuracy of the model's analysis of real-time settlement observation section data. The optimized model can better reflect the actual settlement situation and provide a reliable basis for the safety and stability assessment of railway projects.

[0126] Specifically, the section anomaly judgment method based on settlement observation according to the present invention, step S101, comprises:

[0127] Obtaining an identifier of the settlement observation terminal device, the identifier including a device ID and a serial number, and searching for device parameters corresponding to the settlement observation terminal device in a pre-built knowledge base according to the identifier of the settlement observation terminal device, the device parameters including the accuracy of the device, the measurement range of the device, the calibration period of the device, and the working environment of the device;

[0128] Load the device parameters corresponding to the settlement observation terminal device found in the preset settlement observation knowledge base into the information management system of the settlement observation terminal device, start the self-check program of the settlement observation terminal device, check whether the functions of the settlement observation terminal device are normal, and check whether the functions of the settlement observation terminal device include whether the sensor is working, whether the data transmission is normal, and whether the power status of the settlement observation terminal device is normal;

[0129] By comparing with the preset normal operating status parameters of the settlement observation terminal equipment, analyzing the current operating status of the settlement observation terminal equipment, real-time monitoring and analysis of the output data of the settlement observation terminal equipment, detecting whether there are abnormal fluctuations or deviations from the normal range in the output data of the settlement observation terminal equipment, and obtaining the result of the operating status detection.

[0130] Obtain an identifier of the settlement observation terminal device. The identifier of the settlement observation terminal device includes a device ID and a serial number. The identifier of the settlement observation terminal device is unique and is used to search for information corresponding to a specific device in a pre-built knowledge base.

[0131] According to the obtained device identifier, the device parameters corresponding to the settlement observation terminal device are searched in the pre-built knowledge base. The device parameters include the accuracy, measurement range, calibration cycle and working environment of the device.

[0132] The equipment parameters corresponding to the settlement observation terminal equipment found in the knowledge base are loaded into the equipment information management system, so that the equipment can perform accurate measurement and observation according to the equipment parameters during actual operation.

[0133] Start the self-check program of the settlement observation terminal equipment to conduct a comprehensive check on the equipment's functions, including whether the sensor is working properly, whether the data transmission is smooth, and whether the power status of the equipment is stable. The purpose of the self-check program is to ensure that the equipment is in the best condition before performing the surveying and mapping task.

[0134] The current operating status of the settlement observation terminal equipment is analyzed by comparing it with the preset normal operating status parameters of the settlement observation terminal equipment. At the same time, the output data of the equipment is monitored and analyzed in real time to detect whether there are abnormal fluctuations or deviations from the normal range. This step is to evaluate the performance of the equipment and discover potential problems.

[0135] Based on the execution of the above steps, the operating status detection result of the settlement observation terminal equipment is obtained. The operating status detection result indicates whether the equipment is operating normally or abnormal, providing a basis for subsequent surveying and mapping tasks and data analysis.

[0136] Step S101 ensures that the settlement observation terminal equipment is in a normal state before executing the surveying and mapping task, thereby improving the accuracy and reliability of subsequent settlement observation data and providing a strong guarantee for the safe operation of the railway project.

[0137] Specifically, the section anomaly judgment method based on settlement observation according to the present invention, step S101, comprises:

[0138] Generate an operation status report of the settlement observation terminal device according to the result of the operation status detection, wherein the operation status report of the settlement observation terminal device includes the detection index of the device and whether there is any abnormality in the function;

[0139] The operation status report of the settlement observation terminal device is stored in the information management system, and the device is classified and marked according to the operation status report of the settlement observation terminal device, and the device classification mark includes normal operation and abnormal operation;

[0140] Stop using the equipment classified and marked as operating abnormally.

[0141] Step S101 in the section abnormality judgment method based on settlement observation of the present invention involves comprehensive status detection of the settlement observation terminal equipment. The following is a detailed description of the subsequent contents of this step:

[0142] According to the operating status test results of the settlement observation terminal equipment, a detailed operating status report is generated. This report not only includes various test indicators of the equipment, but also clearly points out whether there are any abnormalities in the equipment function, providing a basis for subsequent equipment management.

[0143] The generated operating status report of the settlement observation terminal equipment is stored in the information management system, which not only facilitates the subsequent query and management of the report, but also realizes the security and traceability of the data.

[0144] According to the content of the operating status report, the settlement observation terminal equipment is classified and marked. The marking clearly indicates the working status of the equipment, which is divided into normal operation and abnormal operation. The classification helps to quickly identify equipment that requires special attention or maintenance.

[0145] For settlement observation terminal equipment marked as operating abnormally, measures are taken to stop using it. The decision is intended to ensure that subsequent settlement observation tasks can be carried out using equipment in good condition, thereby greatly improving the accuracy and reliability of observation data and providing strong guarantees for the safe operation of railway projects.

[0146] Specifically, the section anomaly judgment method based on settlement observation of the present invention, step S102, comprises:

[0147] Determine the observation target, the observation target includes the observed section location, section range and the purpose of the observed section, the purpose of the observed section includes evaluating the railway subgrade stability, railway bridge foundation settlement and railway foundation deformation;

[0148] Acquire engineering data according to the observed section position, the section range and the purpose of observing the section, and determine the geological conditions of the section area, the structural form of the section area and the deformation characteristics of the section area according to the engineering data, wherein the engineering data includes engineering design drawings, geological survey reports and construction plans;

[0149] The geological conditions of the area where the section is located include the distribution of strata, the properties of soil layers and the groundwater level;

[0150] The structural form of the area where the section is located includes the pile foundation arrangement of the railway bridge and the load-bearing structure of the railway.

[0151] Determine the observation target and clarify the specific location of the railway section that needs to be observed, that is, the section location to be observed.

[0152] Determine the specific area covered by the observed section, that is, the section range.

[0153] The purpose of the observation section is clarified, including the assessment of the stability of the railway subgrade, the settlement of the railway bridge foundation, and the deformation of the railway foundation, in order to provide a clear direction for subsequent observations and analysis.

[0154] Obtain engineering data and collect relevant engineering data based on the determined observation targets. Engineering data includes engineering design drawings, geological survey reports, and construction plans, etc. These data are the basis for understanding cross-section conditions, analyzing settlement causes, and predicting abnormal changes.

[0155] Determine the geological conditions and analyze the geological conditions of the section area in detail based on the collected engineering data. The geological conditions include key information such as stratum distribution, soil properties, and groundwater level, which have an impact on the settlement behavior and abnormal changes of the section.

[0156] Determine the structural form and analyze the structural form of the section area, especially the pile foundation arrangement of the railway bridge and the load-bearing structure of the railway. Different structural forms will directly affect the stress and settlement characteristics of the section, so accurate analysis is the key to predicting the settlement behavior of the section.

[0157] In addition to geological conditions and structural forms, deformation characteristics analysis also requires in-depth analysis of the deformation characteristics of the section area.

[0158] The analysis of deformation characteristics helps to understand the settlement behavior of the section more accurately and provide strong support for subsequent abnormal judgment.

[0159] Specifically, the section anomaly judgment method based on settlement observation of the present invention, step S102, comprises:

[0160] Determine the type of observation points for section layout, including the four corners, large corners, 10-15 meters along the rails, both sides of settlement joints or expansion joints, new and old rails or high and low rails, and the intersection of vertical and horizontal rails;

[0161] A cross-section surveying and mapping point model for settlement observation is constructed according to the type of observation points arranged in the cross section. The output content of the cross-section surveying and mapping point model for settlement observation includes the position, number and deformation characteristics of each observation point.

[0162] The types of observation points include the four corners, large corners, 10-15 meters along the track, both sides of the settlement joints or expansion joints, new and old tracks or high and low tracks, and the intersection of vertical and horizontal tracks. These locations are selected to fully cover the key areas where settlement or deformation may occur, and provide accurate data support for subsequent observations.

[0163] According to the determined observation point types, a cross-sectional mapping point model for settlement observation is constructed. The cross-sectional mapping point model for settlement observation is the basis for subsequent observations and data analysis. It ensures that the layout of observation points is both scientific and reasonable and efficient and practical.

[0164] The output content of the cross-sectional mapping point model of settlement observation includes the specific location, number and deformation characteristics of each observation point. The output content information not only provides clear guidance for observers, but also provides a strong basis for subsequent data analysis and abnormal judgment.

[0165] Through the above steps, the present invention can ensure that the layout of observation points is comprehensive and accurate, and the constructed surveying and mapping point model also lays a solid foundation for subsequent settlement observation and abnormal judgment. Such a design not only improves the efficiency and accuracy of observation, but also provides a strong technical guarantee for the safe operation of railway projects.

[0166] Specifically, the section anomaly judgment method based on settlement observation according to the present invention, step S103, comprises:

[0167] Obtain geological survey reports, climate condition data, structural characteristics data and historical observation data for the area where the section is located. The geological survey report includes stratum distribution, soil layer properties, groundwater level and geological conditions;

[0168] The climate condition data includes meteorological data of the area, and the meteorological data of the area includes rainfall, temperature, humidity and wind speed;

[0169] The structural characteristic data include the structural form, material properties and load conditions of the section;

[0170] The historical observation data include control point coordinate data of the cross-section settlement observation historical data in the area, previous observation results and abnormal warning thresholds.

[0171] The geological survey report is data for understanding the geological basis of the section area, including key information such as stratum distribution, soil properties, groundwater level and geological conditions, which will help to establish an accurate settlement prediction model in the future.

[0172] Climate condition data covers the meteorological data of the area, such as rainfall, temperature, humidity, and wind speed. These factors directly affect the moisture, temperature, and stress state of the soil, thereby affecting the settlement rate and deformation mode. By obtaining this data, a more detailed prediction and analysis of the settlement process can be made.

[0173] Structural property data include the structural form, material properties and load conditions of the section, which are essential for understanding the response of the structure to settlement and the deformation characteristics under different load conditions. By analyzing these data, the stability and safety of the section can be evaluated more accurately.

[0174] Historical observation data provides a long-term record of cross-section settlement observations, including control point coordinate data, previous observation results, and abnormal warning thresholds. These data not only help to establish a prediction model, but also provide a reference for setting a reasonable abnormal warning threshold, thereby ensuring that potential settlement anomalies are discovered and handled in a timely manner.

[0175] Step S103 comprehensively obtains data on geology, climate, structure, historical observations, etc. in the area where the section is located, providing solid data support for subsequent settlement prediction and abnormal judgment.

[0176] Specifically, the section anomaly judgment method based on settlement observation according to the present invention, step S103, comprises:

[0177] Obtaining historical cross-section settlement observation influencing factor results, wherein the historical cross-section settlement observation influencing factor results include the influence of geological conditions on settlement rate and deformation mode, the influence of climate conditions on soil moisture, and the influence of temperature stress;

[0178] According to the historical cross-section settlement observation influencing factor results, a preliminary abnormality alert threshold range is set, and the preliminary abnormality alert threshold range is used as the real-time abnormality alert threshold range.

[0179] Set the initial abnormal warning threshold range, collect and analyze historical cross-section settlement observation data, including the impact of geological conditions on settlement rate and deformation mode, the impact of climate conditions on soil moisture, and the impact of temperature stress, etc. These data usually come from geological survey reports, climate condition records, historical observation data, etc.

[0180] Through statistical analysis or expert evaluation, the relationship between various influencing factors and cross-section settlement behavior is analyzed. For example, the distribution of soft soil layers in geological conditions may lead to higher settlement rates, while extreme climate conditions may accelerate changes in soil moisture, which in turn affects settlement. The purpose is to understand the specific effects of different factors on settlement rates and deformation patterns, and provide a basis for setting reasonable abnormal warning thresholds.

[0181] Based on the above analysis results, combined with engineering experience and safety standards, a preliminary abnormal warning threshold range is set. This threshold range should be able to capture settlement changes that may cause safety problems. When setting the threshold, it is necessary to comprehensively consider the influence of geological conditions, climatic conditions, structural characteristics, and historical observation data to ensure the rationality and effectiveness of the threshold.

[0182] The preliminary abnormal warning threshold range is used as the real-time abnormal warning threshold range. During the actual settlement observation process, the settlement data of each measuring point is collected in real time, including deformation rate and total deformation, etc. The real-time collected data is compared and analyzed with the historical data to evaluate whether the current settlement status is normal.

[0183] Compare the real-time settlement data with the initially set abnormal warning threshold range. If the real-time settlement data exceeds the threshold range, it is judged as abnormal settlement and triggers the early warning mechanism. The early warning mechanism may include sound and light alarms, SMS notifications, email reminders and other methods to ensure that relevant personnel can receive abnormal reminders in time.

[0184] In practical applications, the abnormal warning threshold range is dynamically adjusted and optimized according to the actual situation and feedback results of settlement observation. For example, if the threshold set initially is found to be too sensitive or not sensitive enough, it can be adjusted appropriately according to the actual situation. The purpose is to ensure that the abnormal warning threshold range can accurately reflect the actual settlement situation and improve the accuracy and effectiveness of the early warning.

[0185] Specifically, the section anomaly judgment method based on settlement observation of the present invention, step S105, comprises:

[0186] Substituting the real-time settlement observation section data into the optimized section settlement observation point prediction model, the real-time section settlement observation point prediction results are obtained, including:

[0187] Determine the basis for data grouping according to the cross-section surveying and mapping requirements of the settlement observation and the settlement observation terminal equipment information, wherein the basis for data grouping includes time, location and geological conditions;

[0188] According to the data grouping basis, the real-time settlement observation section data are grouped, and the real-time settlement observation section data are grouped including dividing the data into different time periods according to the observation time, and dividing the data into different sections or measuring points according to the location;

[0189] The real-time cross-sectional settlement observation point prediction result is compared with the settlement prediction result of the point to be observed. If the real-time cross-sectional settlement observation point prediction result is inconsistent with the settlement prediction result of the point to be observed, a data accuracy detection process is performed, including:

[0190] Perform quality inspection on each group of data in the grouped real-time settlement observation section data, check the continuity, stability and outliers of each group of data, obtain historical data and design standards corresponding to each group of data, compare and analyze each group of data with the historical data and design standards, check whether each group of data has data points that exceed the allowable range of the design standards, treat the data points that exceed the allowable range of the design standards as outliers, and remove the detected outlier data.

[0191] Substitute the real-time settlement observation section data into the optimized section settlement observation point prediction model to obtain the real-time section settlement observation point prediction results. According to the section mapping requirements of settlement observation and the settlement observation terminal equipment information, the basis for data grouping, including time, location and geological conditions, is determined, which is crucial for subsequent data analysis and abnormal judgment.

[0192] The real-time settlement observation section data are grouped according to the data grouping basis, including dividing the data into different time periods according to the observation time, so as to analyze the settlement conditions in different time periods; and dividing the data into different sections or measuring points according to the location, so as to locate the abnormal position more accurately.

[0193] Compare the predicted results of the real-time cross-section settlement observation points with the predicted results of the settlement of the points to be observed. If the two are inconsistent, it means that there may be data errors or abnormalities, and the data accuracy detection process needs to be carried out.

[0194] The data accuracy detection process includes accuracy detection of the optimized cross-section settlement observation point prediction model and accuracy group detection of the data collected by the surveying and mapping task executable surveying and mapping equipment. If there is abnormal data in the detection, a data collection error warning message will be generated; if there is no abnormal data, the settlement observation point analysis model will be optimized.

[0195] When setting up the data accuracy detection process, you also need to set the number of detections and the expected cross-sectional settlement observation accuracy value for data accuracy detection. When the detection process reaches the number of detections or reaches the expected accuracy value, stop the detection.

[0196] Finally, in the data grouping test, each group of data is tested for quality, checking the continuity, stability and outliers of the data. Data points that exceed the allowable range of the design standard are removed as outliers to ensure the accuracy and reliability of the data.

[0197] Specifically, the section anomaly judgment method based on settlement observation of the present invention further includes:

[0198] Receive and store the settlement observation data of each measuring point, wherein the settlement observation data of each measuring point includes the deformation rate and the total deformation. When it is detected that the deformation rate or the uplift rate of the total deformation exceeds the set dynamic threshold, the server will automatically trigger an abnormal settlement or abnormal uplift reminder;

[0199] The server will automatically trigger abnormal subsidence or abnormal uplift reminders via SMS and email to notify management personnel in real time.

[0200] The section abnormality judgment method based on settlement observation described in the present invention plays a role in the safe operation of railway engineering. It not only involves the reception and storage of settlement observation data, but also includes automatic detection and real-time reminder of abnormal settlement or uplift. The following is a detailed description of the method:

[0201] The system receives settlement observation data from each measuring point, which includes key information such as deformation rate and total deformation. The data is properly stored in the system for subsequent analysis and comparison, thus ensuring the continuity and accuracy of settlement observation.

[0202] When the system detects that the deformation rate or the uplift rate of the total deformation exceeds the preset dynamic threshold, it will automatically trigger an abnormal settlement or abnormal uplift reminder. The dynamic threshold is set based on historical data, geological conditions, climate conditions and other factors, aiming to timely detect potential settlement or uplift risks and ensure project safety.

[0203] When an abnormal alert is triggered, the server will quickly send the abnormal settlement or abnormal uplift alert to the relevant managers in real time via SMS and email. The real-time notification mechanism ensures that managers can respond quickly and take necessary measures to deal with possible settlement or uplift problems in a timely manner, thereby effectively reducing risks.

[0204] Through this series of operations and processes, the cross-section abnormality judgment method based on settlement observation described in the present invention not only improves the response speed to settlement or uplift abnormalities, but also enhances the safety of railway engineering. At the same time, based on the collected settlement observation data, managers can more scientifically formulate and optimize the maintenance strategy of railway engineering, reduce maintenance costs, and improve maintenance efficiency. In addition, the implementation and application of this method also helps to improve the technical level of settlement observation and abnormality judgment of railway engineering, and promote the progress and development of railway engineering technology.

[0205] Specifically, the section anomaly judgment method based on settlement observation of the present invention further includes:

[0206] The server establishes reminder levels for multiple measuring points. For multiple measuring points in the same section, the server compares the reminder levels of multiple measuring points.

[0207] If the reminder levels of different measuring points in the same section are different, the server will select the highest level as the final reminder level of the section;

[0208] When the final alert level of the section is determined, the server will automatically generate alert information, including specific data of the anomaly, the determined alert level, and handling suggestions;

[0209] The reminder information will be sent to the management via the preset communication channels.

[0210] The section abnormality judgment method based on settlement observation described in the present invention is of great significance in railway engineering safety monitoring. The method establishes the reminder levels of multiple measuring points through a server, and compares multiple measuring points in the same section to determine the final reminder level of the section. The following is a detailed description of the method:

[0211] Establishment of reminder levels,The server sets reminder levels for multiple measuring points in the railway project. These levels are used to evaluate the degree of abnormal settlement of each measuring point and provide a basis for subsequent analysis and processing.

[0212] Comparison of alert levels,For multiple measuring points in the same section, the server will carefully compare their alert levels.,This step is to comprehensively evaluate the overall settlement of the section and ensure that no potential anomalies are missed.

[0213] Determination of the final alert level: If the alert levels of different measuring points in the same section are different, the server will intelligently select the highest level as the final alert level of the section. This decision ensures that even if only one measuring point in the section has a highly abnormal settlement, the entire section will be marked with the corresponding alert level, thus attracting the attention of management personnel.

[0214] Automatic generation of reminder information: When the final reminder level of the section is determined, the server will automatically generate detailed reminder information. This information includes specific data of the abnormality (such as deformation rate, total deformation, etc.), the determined reminder level, and targeted processing suggestions, providing comprehensive decision support for managers.

[0215] The generated reminder information will be sent to the management personnel in real time through the preset communication channels (such as SMS, email, etc.). This step enables the management personnel to quickly receive abnormal reminders and take appropriate measures to deal with potential settlement problems in time, thereby ensuring the safe operation of the railway project.

[0216] Through this series of carefully designed processes, the section anomaly judgment method based on settlement observation described in the present invention not only improves the efficiency of discovering and handling settlement anomalies in railway projects, but also significantly enhances the safety and stability of railway projects.

[0217] Step S106, comparing the optimized settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the comparison result of the settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point meets the preset error range, then using the section abnormality reminder threshold in the surveying and mapping parameter requirement information to compare data with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point. If the settlement prediction result of the point to be observed with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point are within the section abnormality reminder threshold range in the surveying and mapping parameter requirement information, then generating second section abnormality warning information;

[0218] If the comparison result of the optimized settlement prediction result of the point to be observed and the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point do not meet the preset error range, the real-time settlement observation section data is substituted into the optimized section settlement observation point prediction model to obtain the real-time section settlement observation point prediction result, and the real-time section settlement observation point prediction result is compared with the settlement prediction result of the point to be observed. If the real-time section settlement observation point prediction result is inconsistent with the settlement prediction result of the point to be observed, a data accuracy detection process is performed;

[0219] The data accuracy detection process includes performing an accuracy detection on the optimized cross-section settlement observation point prediction model. If the accuracy detection of the optimized cross-section settlement observation point prediction model is qualified, then performing an accuracy group detection on the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task. If there is abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then generating data collection error warning information. If there is no abnormal data in the accuracy group detection of the data collected by the surveying and mapping equipment that can be executed for the surveying and mapping task, then optimizing the settlement observation point analysis model, using the optimized settlement observation point analysis model to analyze the real-time settlement observation cross-section data, setting the number of detection times of the data accuracy detection process and the expected cross-section settlement observation accuracy value of the data accuracy detection, when the data accuracy detection process reaches the number of detection times or reaches the expected cross-section settlement observation accuracy value, the data accuracy detection process stops.

[0220] The present invention provides a section anomaly judgment method based on settlement observation, which aims to solve the problem of being interfered by various factors during the observation process, affecting the accuracy of the observation data, and pre-detecting errors. The following are the main steps of the method:

[0221] Obtain the cross-section surveying and mapping requirements of settlement observation and the information of settlement observation terminal equipment, match the equipment parameters in the preset settlement observation knowledge base, load the matched equipment parameters to the terminal equipment, and then perform operation status detection. Detect the operation status of the settlement observation terminal equipment to ensure that the equipment is operating normally. Use the equipment that is operating normally as the executable equipment for the surveying and mapping task, and stop using the equipment that is operating abnormally.

[0222] Analyze the cross-section mapping requirements of settlement observation to obtain task information, equipment requirement information and parameter requirement information. Based on this information, generate the points to be observed.

[0223] A database is established, and the coordinate data of the control points are retrieved for coordinate matching to obtain the coordinate information of the points to be observed. Then, a prediction model is built based on historical data and current needs, and the settlement prediction results of the points to be observed are output and compared with the preset abnormal warning threshold.

[0224] If the prediction result is not within the abnormal warning threshold range, the real-time settlement observation section data will be obtained and compared with the prediction result. If the error value is greater than the prediction error range, the prediction model and analysis model will be optimized and compared again.

[0225] If the optimized result still does not meet the preset error range, the data accuracy detection process will be carried out, which includes model accuracy detection and data grouping detection. When abnormal data is found, a data collection error warning message will be generated; if there is no abnormal data, the analysis model will continue to be optimized until the number of detections or the expected accuracy value is reached.

[0226] The system will receive and store the settlement observation data of each measuring point. When an abnormality is detected, it will automatically trigger an alert and notify the management staff in real time via SMS and email.

[0227] The server will also establish reminder levels for multiple measuring points and compare the reminder levels of multiple measuring points in the same section. After determining the final reminder level, a reminder message will be automatically generated and sent to the management personnel through the preset communication channel.

[0228] The present invention can effectively solve the interference of various factors that may occur during the observation process, improve the accuracy of the observation data, and pre-discover abnormal cross-section data during the settlement observation process.

[0229] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if the 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 the modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. A method for determining cross-section anomaly based on settlement observation, characterized in that: include: Step S101, obtaining the cross-sectional surveying and mapping requirements of settlement observation and the settlement observation terminal equipment information, matching the settlement observation terminal equipment parameters in a preset settlement observation knowledge base according to the cross-sectional surveying and mapping requirements of the settlement observation, obtaining the equipment parameters corresponding to the settlement observation terminal equipment, loading the equipment parameters corresponding to the settlement observation terminal equipment into the settlement observation terminal equipment, performing an operation status detection on the settlement observation terminal equipment, and obtaining the operation status detection result of the settlement observation terminal equipment; The detection result of the operation status of the settlement observation terminal equipment includes the equipment information of the settlement observation terminal operating normally and the equipment information of the settlement observation terminal operating abnormally, and the surveying and mapping equipment corresponding to the equipment information of the settlement observation terminal operating normally is used as the surveying and mapping equipment executable by the surveying and mapping task; Step S102, parsing the cross-section surveying and mapping requirements of the settlement observation, obtaining cross-section settlement observation task information, surveying and mapping equipment terminal requirement information, and surveying and mapping parameter requirement information, wherein the surveying and mapping parameter requirement information includes a cross-section abnormality reminder threshold and a settlement observation terminal equipment operation abnormality reminder threshold, and the cross-section settlement observation task information includes cross-section position information, deformation rate surveying and mapping tasks, and total deformation surveying and mapping tasks, substituting the cross-section settlement observation task information into a preset cross-section surveying and mapping point model of the settlement observation, and generating cross-section points to be observed for the settlement observation; Step S103, establishing a database for data storage, retrieving the control point coordinate data of the corresponding position area in the database according to the section position information, performing coordinate matching on the section observation point to be observed based on the control point coordinate data, obtaining the coordinate information of the point to be observed, retrieving the corresponding section settlement observation history data in the database according to the coordinate information of the point to be observed, obtaining the settlement observation history data of the coordinate surface of the point to be observed, the settlement observation history data of the coordinate surface of the point to be observed including the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold, and constructing a section settlement observation point prediction model through the difference between the historical section abnormality reminder threshold and the section abnormality reminder threshold; Step S104, substituting the coordinate information of the point to be observed into the cross-section settlement observation point prediction model, outputting the settlement prediction result of the point to be observed, using the cross-section abnormality reminder threshold in the surveying and mapping parameter requirement information to compare data with the settlement prediction result of the point to be observed, and if the settlement prediction result of the point to be observed is within the cross-section abnormality reminder threshold in the surveying and mapping parameter requirement information, generating first cross-section abnormality warning information; If the settlement prediction result of the observation point is not within the section abnormality warning threshold range in the surveying and mapping parameter requirement information, then the real-time settlement observation section data collected by the surveying and mapping task executable surveying and mapping equipment is obtained, and the real-time settlement observation section data is substituted into the preset settlement observation point analysis model to obtain the real-time deformation rate and the real-time total deformation of the settlement observation point, and then step 105 is executed; Step S105, comparing the real-time deformation rate and the real-time total deformation of the settlement observation point with the settlement prediction result of the point to be observed, and obtaining the error value between the prediction and the actual observation of the point to be observed; if the error value between the prediction and the actual observation of the point to be observed is greater than the prediction error range, optimizing the cross-section settlement observation point prediction model and the settlement observation point analysis model to obtain an optimized cross-section settlement observation point prediction model and an optimized settlement observation point analysis model; using the optimized cross-section settlement observation point prediction model to perform data processing on the coordinate information of the point to be observed, and obtaining an optimized settlement prediction result of the point to be observed; using the optimized settlement observation point analysis model to perform data processing on the real-time settlement observation section data, and obtaining an optimized real-time deformation rate and a real-time total deformation of the settlement observation point; Step 106, comparing the optimized settlement prediction result of the observation point with the optimized real-time deformation rate of the settlement observation point and the real-time total deformation of the settlement observation point to generate abnormal warning information of the second section.

2. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: The step S101 includes: Step S1011, obtaining an identifier of the settlement observation terminal device, the identifier including a device ID and a serial number, searching for device parameters corresponding to the settlement observation terminal device in a pre-built knowledge base according to the identifier of the settlement observation terminal device, the device parameters including the accuracy of the device, the measurement range of the device, the calibration period of the device, and the working environment of the device; Step S1012, loading the device parameters corresponding to the settlement observation terminal device found in the preset settlement observation knowledge base into the information management system of the settlement observation terminal device, starting the self-check program of the settlement observation terminal device, checking whether the functions of the settlement observation terminal device are normal, and checking whether the functions of the settlement observation terminal device include whether the sensor is working, whether the data transmission status is normal, and whether the power status of the settlement observation terminal device is normal; Step S1013, by comparing with the preset normal operating status parameters of the settlement observation terminal equipment, analyzing the current operating status of the settlement observation terminal equipment, real-time monitoring and analysis of the output data of the settlement observation terminal equipment, and obtaining the result of the operating status detection, the analysis of the output data of the settlement observation terminal equipment includes: detecting whether there is abnormal fluctuation in the output data of the settlement observation terminal equipment, and monitoring whether the output data of the settlement observation terminal equipment deviates from the normal range.

3. The method for determining cross-section anomaly based on settlement observation according to claim 2, characterized in that: The step S101 includes: Step S1014, generating an operation status report of the settlement observation terminal device according to the result of the operation status detection, wherein the operation status report of the settlement observation terminal device includes the detection index of the device and the function completion status of the device; Step S1015, storing the operation status report of the settlement observation terminal device in the information management system, and classifying and marking the device according to the operation status report of the settlement observation terminal device, wherein the device classification mark includes normal operation and abnormal operation; Step S1016: Stop using the device that is marked as abnormally operating.

4. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: The step S102 includes: Step S1021, determining the observation target, wherein the observation target includes the observed section position, section range and purpose of the observed section, wherein the purpose of the observed section includes evaluating the railway subgrade stability, railway bridge foundation settlement and railway foundation deformation; Step S1022, acquiring engineering data according to the observed section position, the section range and the purpose of the observed section, and determining the geological conditions of the section area, the structural form of the section area and the deformation characteristics of the section area according to the engineering data, wherein the engineering data includes engineering design drawings, geological survey reports and construction plans, the geological conditions of the section area include stratum distribution, soil layer properties and groundwater level, and the structural form of the section area includes the pile foundation arrangement of the railway bridge and the load-bearing structure of the railway.

5. The method for determining cross-section anomaly based on settlement observation according to claim 4, characterized in that: The step S102 includes: Step S1023, determining the type of observation points for section layout, wherein the types of observation points for section layout include four corners, large corners, 10-15 meter areas along the rails, both sides of settlement joints or expansion joints, new and old rails or high and low rails, and intersections of vertical and horizontal rails; Step S1024, constructing a cross-section surveying and mapping point model for settlement observation according to the cross-section layout observation point type, the output content of the cross-section surveying and mapping point model for settlement observation includes the position, number and deformation characteristics of each observation point.

6. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: The step S103 includes: Step S1031, obtaining a geological survey report, climate condition data, structural characteristic data, and historical observation data of the area where the section is located, wherein the geological survey report includes stratum distribution, soil layer properties, groundwater level, and geological conditions; The climate condition data includes meteorological data of the area, which includes rainfall, temperature, humidity and wind speed; the structural characteristic data includes the structural form, material properties and load conditions of the section; the historical observation data includes the control point coordinate data of the section settlement observation history data of the area, previous observation results and abnormal warning threshold.

7. The method for determining cross-section anomaly based on settlement observation according to claim 6, characterized in that: The step S103 further includes: Step S1032, obtaining the influencing factors of historical cross-section settlement observation, wherein the influencing factors of historical cross-section settlement observation include the influence of geological conditions on settlement rate and deformation mode, the influence of climate conditions on soil moisture, and the influence of temperature stress; Step S1033, according to the historical cross-section settlement observation influencing factor results, a preliminary abnormality alert threshold range is set, and the preliminary abnormality alert threshold range is used as the real-time abnormality alert threshold range.

8. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: The step S105 includes: Step S1051, determining the basis for data grouping according to the cross-section mapping requirements of the settlement observation and the settlement observation terminal equipment information, the basis for data grouping including time, location and geological conditions; Step S1052, grouping the real-time settlement observation section data according to the data grouping basis, wherein the real-time settlement observation section data grouping includes dividing the data into different time periods according to the observation time, and dividing the data into different sections or measuring points according to the location; Step S1053, perform quality inspection on each group of data in the grouped real-time settlement observation section data, check the continuity, stability and outliers of each group of data, obtain the historical data and design standards corresponding to each group of data, compare and analyze each group of data with the historical data and design standards, check whether each group of data has data points that exceed the allowable range of the design standards, treat the data points that exceed the allowable range of the design standards as outliers, and remove the detected outlier data.

9. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: Also includes: Receive and store the settlement observation data of each measuring point, wherein the settlement observation data of each measuring point includes the deformation rate and the total deformation. When it is detected that the deformation rate or the uplift rate of the total deformation exceeds the set dynamic threshold, the server will automatically trigger an abnormal settlement or abnormal uplift reminder; The server will automatically trigger abnormal subsidence or abnormal uplift reminders and notify management personnel in real time via SMS and email; The server establishes reminder levels for multiple measuring points. For multiple measuring points in the same section, the server compares the reminder levels of multiple measuring points. If the alert levels of different measuring points in the same section are different, the server will select the highest level as the final alert level of the section; When the final alert level of the section is determined, the server will automatically generate alert information, including specific data of the anomaly, the determined alert level, and processing suggestions.

10. The method for determining cross-section anomaly based on settlement observation according to claim 1, characterized in that: include: Compare the optimized settlement prediction results of the points to be observed with the optimized real-time deformation rate of the settlement observation points and the real-time total deformation of the settlement observation points. If the comparison results of the optimized settlement prediction results of the points to be observed with the optimized real-time deformation rate of the settlement observation points and the real-time total deformation of the settlement observation points meet the preset error range, use the section abnormality reminder threshold in the surveying and mapping parameter requirement information to compare the data with the optimized real-time deformation rate of the settlement observation points and the real-time total deformation of the settlement observation points. If the optimized settlement prediction results of the points to be observed with the optimized real-time deformation rate of the settlement observation points and the real-time total deformation of the settlement observation points are within the section abnormality reminder threshold range in the surveying and mapping parameter requirement information, generate a second section abnormality warning information; If the comparison result of the optimized settlement prediction result of the point to be observed and the optimized real-time deformation rate and real-time total deformation of the settlement observation point do not meet the preset error range, the real-time settlement observation section data is substituted into the optimized section settlement observation point prediction model to obtain the real-time section settlement observation point prediction result, and the real-time section settlement observation point prediction result is compared with the settlement prediction result of the point to be observed. If the real-time section settlement observation point prediction result is inconsistent with the settlement prediction result of the point to be observed, a data accuracy detection process is performed; the data accuracy detection process includes performing an accuracy detection on the optimized section settlement observation point prediction model If the accuracy test of the optimized cross-section settlement observation point prediction model is qualified, the accuracy grouping test is performed on the data collected by the surveying and mapping equipment that can be executed by the surveying and mapping task. If there is abnormal data in the accuracy grouping test of the data collected by the surveying and mapping equipment that can be executed by the surveying and mapping task, data collection error warning information is generated. If there is no abnormal data in the accuracy grouping test of the data collected by the surveying and mapping task that can be executed by the surveying and mapping equipment, the settlement observation point analysis model is optimized, and the real-time settlement observation section data is analyzed using the optimized settlement observation point analysis model. The detection times of the data accuracy detection process and the data accuracy detection expected cross-section settlement observation point are set. When the data accuracy detection process reaches the detection times or reaches the expected section settlement observation accuracy value, The data accuracy check process stops.

Images