Engineering deformation monitoring method and system based on big data

Abstract

The invention discloses an engineering deformation monitoring method and system based on big data, and relates to the technical field of intelligent monitoring, and the method comprises the following steps: setting a screening standard, screening first data, carrying out analysis to obtain a first deformation rate, executing a first operation, setting a key subspace, carrying out first regulation and control and second marking, and carrying out second analysis to obtain an influence relationship. According to the method, after subspace and sensitivity secondary subdivision and actual measurement rate standard deviation reduction are carried out and meteorological and time baseline coupling models are introduced, a data, model and decision closed loop is realized, the operation and maintenance risk is reduced, the method is suitable for three data sources of BIM, point cloud and grids, various engineering types such as dams, fill, bridges, landslides and subway tunnels are covered, and the method is suitable for large-scale popularization and application. Meteorological and geotechnical parameter tables are loosely coupled with the algorithm module, and can be directly popularized to different climate regions and geological conditions by updating a parameter library without modifying core codes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, and in particular to an engineering deformation monitoring method and system based on big data. BACKGROUND

[0002] In recent years, engineering deformation monitoring has entered the intelligent era of "sub-millimeter accuracy, second-level response, AI self-diagnosis, digital twin closed loop", evolved to autonomous monitoring driven by "6G sensing integration, AIGE zero code, quantum sensing", and achieved millimeter-level or even sub-millimeter-level displacement second-level collection and backhaul through the cooperation of Beidou-3, InSAR, unmanned aerial vehicle laser, distributed optical fiber and 5G / 6G communication. Edge AI completes millisecond-level anomaly identification at the base station or airborne end, uploads only features to save bandwidth, and realizes real-time visualization through UE5 digital twin. Typical engineering such as high-speed railway bridge, subway tunnel, dam, mine and ancient building has been widely applied, and the accident rate and maintenance cost have been significantly reduced.

[0003] At present, a bridge deformation monitoring method is disclosed in Chinese patent application CN117029708A. The method determines the landmark points, support reference points and multiple measuring points of the bridge to be measured, obtains the front view image and the rotated image of the bridge to be measured, takes the front view image as the reference image, takes the same named points in the overlapping area of the front view image and the rotated image as the constraint, projects and transforms the rotated image to the reference image to obtain the equivalent front view image, uses the SIFT algorithm to perform feature matching on the reference image and the equivalent front view image to obtain high-precision same named points, obtains the accurate relative orientation elements of the equivalent front view image according to the high-precision same named points and in combination with the bundle adjustment method, splices the reference image and the equivalent front view image according to the accurate relative orientation elements to obtain the panoramic image of the bridge to be measured, and obtains the deformation values of the multiple measuring points of the bridge to be measured according to the panoramic image, the landmark points and the support reference points to obtain the deformation curve. However, the related art does not screen and further analyze the part of the engineering according to the deformation degree algorithm, which is not conducive to the simplicity of data analysis, and does not regulate the monitoring time baseline of the satellite according to the influencing factors, which is not conducive to the accuracy and customization of detection. SUMMARY

[0004] The technical problem solved by the present application is that the related art does not screen and further analyze the part of the engineering according to the deformation degree algorithm, which is not conducive to the simplicity of data analysis, and does not regulate the monitoring time baseline of the satellite according to the influencing factors, which is not conducive to the accuracy and customization of detection.

[0005] To solve the above technical problems, the present application provides the following technical solutions: In a first aspect, an engineering deformation monitoring method based on big data includes the following steps: Step S100, selecting any engineering subspace, setting a screening standard, screening the first data according to the screening standard, analyzing the first data to obtain the first deformation rate, executing the first operation according to the first deformation rate, and marking the first engineering subspace; Step S200, in response to the first operation, setting a key subspace, performing a first regulation on the time baseline of the key subspace, and marking the key subspace according to the first regulation and the first deformation rate after the first regulation; Step S300, performing a second analysis on the related data, the first mark and the second mark to obtain the influence relationship of the meteorological data on the time baseline and the influence relationship of the engineering subspace distribution parameter on the time baseline.

[0006] As a preferred scheme of the engineering deformation monitoring method based on big data, before setting the screening standard, the to-be-monitored engineering is segmented, the segmentation includes semantic segmentation, parameter segmentation, obtaining engineering subspace and automatically numbering, and outputting engineering subspace and its number, wherein the number of engineering subspace is represented as X i , i is a natural number; The semantic segmentation is performed by an open source tool and a classification manager, the three-dimensional model of the to-be-monitored engineering is segmented, the semantic representation is the name of the component of the engineering, IFC is opened, the classification option is clicked, the independent model is created, and N independent objects are obtained; The parameter segmentation includes setting the thickness mutation of the compressible layer to 2 meters as the first segmentation condition, setting the slope threshold to 10 degrees as the second segmentation condition, setting the minimum point number to 1000 as the third segmentation condition, and segmenting the N independent objects to obtain M independent objects; According to the sequence of the segmentation software processing, the M independent objects are automatically numbered, the M independent objects are recorded as engineering subspace, and the number of the M independent objects is recorded as the number of the engineering subspace.

[0007] As a preferred scheme of the engineering deformation monitoring method based on big data, after the to-be-monitored engineering is segmented, any engineering subspace is selected, and a screening standard is set, the screening standard is that the time baseline is the first number of days, the time baseline is represented as the interval time length of SAR detection, wherein the first number of days is obtained by the time baseline of the engineering of the same type as the to-be-monitored engineering, and the first number of days is represented as the average value of the time baseline of the engineering of the same type as the to-be-monitored engineering; The first data is screened according to the screening standard, the first data is represented as each piece of historical monitoring data corresponding to a periodicity of a first number of days, the historical monitoring data is represented as a SAR image, the SAR image is represented as an image of each pixel point on the surface of the engineering subspace photographed by a satellite with a spatial baseline of a first distance, and the emitted radar wavelength is a first wavelength and the time baseline is the first number of days, and the spatial baseline is represented as the distance between the geometric centers of any one set of two satellites for photographing; The deformation phase corresponding to any SAR image is extracted, the deformation phase is converted into a deformation rate according to the InSAR technology, the deformation rate at each pixel point of the engineering subspace is traversed, the average value of the deformation rate at each pixel point is calculated, and the average value of the deformation rate at each pixel point is recorded as a first deformation rate.

[0008] As a preferred scheme of the engineering deformation monitoring method based on big data, wherein: a first operation is performed according to the first deformation rate, the first operation includes first marking the engineering subspace, and setting a key engineering subspace; The setting method of the first operation includes: The first value is set as a deformation rate threshold value, any engineering subspace is selected, the first deformation rate corresponding to the engineering subspace is compared with the first value, when the first deformation rate is less than or equal to the first value, the first operation is set as first marking the engineering subspace, and when the first deformation rate is greater than the first value, the first operation is set as setting the key engineering subspace.

[0009] As a preferred scheme of the engineering deformation monitoring method based on big data, wherein: when the first operation is the first marking of the engineering subspace, the number of the corresponding engineering subspace is marked red, and the first number of days is added after the number of the engineering subspace, and the first marking is represented as X i And the first number of days, a first folder is created, and the first marking is stored in the first folder; When the first operation is setting the key engineering subspace, a second folder is created, the number of the corresponding engineering subspace and the corresponding second data backup are stored in the second folder, the second data is represented as each piece of historical monitoring data of the key engineering subspace, and each engineering subspace in the second folder is set as the key engineering subspace.

[0010] As a preferred scheme of the engineering deformation monitoring method based on big data, wherein: the first change amount is set as a change gradient of the first number of days, and the original time baseline of the key engineering subspace is first regulated according to the first change amount, that is, the first number of days is first regulated, and the first regulation is represented as continuous reduction, and the reduced first number of days is set as a new time baseline. Select any new time baseline, from the starting time point of the historical monitoring data, every interval of the new time baseline, select the historical monitoring data, and set the selected historical monitoring data as the data to be analyzed; Traverse each new time baseline to obtain the data to be analyzed corresponding to each new time baseline.

[0011] As a preferred scheme of the engineering deformation monitoring method based on big data, in the order from large to small according to the new time baseline, the first deformation rate corresponding to the new time baseline is continuously obtained; Until the first deformation rate corresponding to the new time baseline is less than or equal to the first value, stop continuously reducing the first number of days, and obtain the regulated time baseline at this time, denoted as the key number of days; The second mark of the key subspace is represented as the number of the key subspace and the key time baseline, and the second mark is represented as X i And the key time baseline.

[0012] As a preferred scheme of the engineering deformation monitoring method based on big data, wherein the related data includes meteorological data and engineering subspace distribution parameters; The meteorological data includes annual average precipitation, daily average wind speed, annual average air humidity, annual temperature range and annual average snow depth; The engineering subspace distribution parameters include compressible layer thickness, fill thickness, distance from water source, ground slope, daily average load of building, groundwater level depth and vegetation coverage.

[0013] As a preferred scheme of the engineering deformation monitoring method based on big data, wherein the second analysis of the related data, the first mark and the second mark is performed to obtain the influence relationship of the meteorological data on the time baseline, and the influence relationship of the engineering subspace distribution parameters on the time baseline, and the method comprises: Calculate the average value of the first number of days corresponding to the first mark and the key number of days corresponding to the second mark, denoted as the first average value, and perform multiple regression analysis with the first average value as the dependent variable and the meteorological data as the independent variable to obtain the first multiple regression equation, denoted as the influence relationship of the meteorological data on the time baseline; Calculate the first difference value of the first number of days corresponding to the first mark and the key number of days corresponding to the second mark, and perform multiple regression analysis with the first difference value as the dependent variable and the engineering subspace distribution parameters as the independent variable to obtain the second multiple regression equation, denoted as the influence relationship of the engineering subspace distribution parameters on the time baseline; By inputting the meteorological data into the influence relationship of the meteorological data on the time baseline, the first average value of the new project of the same type as the monitored project is obtained, and the corresponding key day number is inversely calculated according to the first day number and the first average value of the new project. The first difference value of the first day number and the key day number corresponding to the new project is calculated, and the time baseline of each engineering subspace corresponding to the new project is obtained by inputting the corresponding first difference value into the influence relationship of the engineering subspace distribution parameter on the time baseline.

[0014] In a second aspect, the big data-based engineering deformation monitoring system comprises a marking module, an analysis module and a construction module. The marking module selects any engineering subspace, sets a screening standard, screens the first data according to the screening standard, analyzes the first data, obtains the first deformation rate, executes the first operation according to the first deformation rate, and marks the first mark of the engineering subspace. The analysis module responds to the first operation, sets a key subspace, performs the first regulation and control on the time baseline of the key subspace, and performs the second marking on the key subspace according to the first deformation rate after the first regulation and control. The construction module performs the second analysis on the related data, the first mark and the second mark, obtains the influence relationship of the meteorological data on the time baseline and the influence relationship of the engineering subspace distribution parameter on the time baseline.

[0015] The beneficial effects of the present application are: through the secondary subdivision of the subspace and the sensitivity, the deformation gradient in each calculation unit is ensured to be less than 3 millimeters per first day number, the standard deviation of the measured rate is reduced, after introducing the meteorological and time baseline coupling model, the atmospheric phase residual is reduced, the annual rate error is compressed, the output meteorological and time baseline and distribution parameter and time baseline double model can be directly embedded into the digital twin platform, realizing the data, model and decision closed loop, providing an interpretable sensitive factor ranking for the operation and maintenance unit, assisting in formulating targeted reinforcement, drainage or loading scheme, reducing operation and maintenance risk, the method is suitable for BIM, point cloud and grid three kinds of data sources, covering various engineering types such as dam, filling, bridge, landslide and subway tunnel, and the meteorological and geotechnical parameter table and the algorithm module are loosely coupled, which can be directly popularized to different climate zones and geological conditions by updating the parameter library without modifying the core code. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The basic flowchart of the big data-based engineering deformation monitoring method provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all embodiments.

[0018] Embodiments, with reference to Figure 1 For an embodiment of the present application, a big data-based engineering deformation monitoring method is provided, comprising the following steps: Step S100, selecting any engineering subspace, setting a screening standard, screening first data according to the screening standard, analyzing the first data to obtain a first deformation rate, performing a first operation according to the first deformation rate, and marking the first engineering subspace; Step S200, in response to the first operation, setting a key subspace, performing a first control on the time baseline of the key subspace, and marking the key subspace according to the first deformation rate after the first control; Step S300, performing a second analysis on the related data, the first mark and the second mark, obtaining the influence relationship of meteorological data on the time baseline and the influence relationship of engineering subspace distribution parameters on the time baseline.

[0019] The present application ensures that the internal deformation gradient of each calculation unit is less than 3 millimeters per first day through subspace and sensitivity secondary subdivision, reduces the standard deviation of the measured rate, reduces the atmospheric phase residual after introducing the meteorological and time baseline coupling model, compresses the annual rate error, and outputs the meteorological and time baseline and the distribution parameter and time baseline double model, which can be directly embedded in the digital twin platform to realize the data, model and decision closed loop, provide an interpretable sensitive factor ranking for the operation and maintenance unit, assist in formulating targeted reinforcement, drainage or loading schemes, reduce operation and maintenance risks, the method is suitable for BIM, point cloud and grid three kinds of data sources, covers various engineering types such as dams, fills, bridges, landslides and subway tunnels, and the meteorological and geotechnical parameter table and the algorithm module are loosely coupled, which can be directly promoted to different climate zones and geological conditions by updating the parameter library without modifying the core code.

[0020] Before setting the screening standard, the to-be-monitored engineering is segmented, the segmentation includes semantic segmentation, parameter segmentation, obtaining engineering subspace and automatically numbering, and outputting the engineering subspace and its number, wherein the number of the engineering subspace is represented as X i , i is a natural number; The semantic segmentation is segmented by an open source tool and a classification manager, the three-dimensional model of the to-be-monitored engineering is segmented, the semantics is represented as the name of the constituent part of the engineering, IFC is opened, the classification option is clicked, the independent model is created, and N independent objects are obtained; The parameter segmentation includes setting a compressible layer thickness mutation of 2 meters as a first segmentation condition, setting a slope threshold of 10 degrees as a second segmentation condition, setting a minimum point number of 1000 as a third segmentation condition, segmenting N independent objects, and obtaining M independent objects. According to the processing sequence of the segmentation software, the M independent objects are automatically numbered, and the M independent objects are recorded as engineering subspaces, and the numbers of the M independent objects are recorded as the numbers of the engineering subspaces.

[0021] In a specific implementation, using open source BlenderBIM and classification manager, semantic splitting is automatically completed in 3 minutes, completely getting rid of traditional CAD manual cutting, and the segmentation efficiency is improved by more than 10 times. Parameter segmentation, such as thickness mutation of 2 meters, slope of 10 degrees, and minimum of 1000 points, is bound with the numbering process, M engineering subspaces are output at one time, avoiding subsequent manual correspondence errors, ensuring that the data link is 100% traceable, taking the compressible layer thickness mutation greater than or equal to 2 meters as the first cutting surface, ensuring that the settlement gradient in the same subspace is less than 3 millimeters per first day, the standard deviation of the measured rate is reduced by 35%, the slope threshold of 10 degrees automatically separates the rear edge and the front edge of the slope, the rate difference of different blocks of the landslide can be independently solved, avoiding the 5 to 10 millimeters per first day error caused by mixed calculation, and the minimum of 1000 points ensures that each Xi still has more than or equal to 50 high-coherent pixels after SAR multi-view, meeting the first-level precision requirement of the “Geological Disaster InSAR Monitoring Specification”, the numbering order is consistent with the software processing time sequence, and the semantics, geometry, and parameter versions are naturally recorded, facilitating subsequent big data regression as Panel data keys, Xi encoding can be seamlessly embedded in the blockchain or digital twin platform, realizing subspace-level deformation data tamper-proofing and life cycle management, and pre-cutting a homogeneous unit with deformation sensitivity, so that subsequent screening standards only need to be run once to locate abnormal areas, the calculation amount is reduced from the whole image level to the subspace level, and the CPU time is saved by 60%. Due to the controlled thickness, slope, and point number, the overall image rejection rate is reduced from 25% to 8%, effectively improving the SAR data utilization rate. The segmentation conditions (2 meters / 10 degrees / 1000 points) are all based on national standards and can be parameterized and adjusted with one key, which is suitable for dams, fills, bridges, landslides, subway foundation pits, and other types of engineering.

[0022] After the to-be-monitored engineering is segmented, any engineering subspace is selected, and a screening standard is set. The screening standard is a time baseline of the first day, and the time baseline is represented as the interval of SAR detection. The first day is obtained by the time baseline of the same type of engineering as the to-be-monitored engineering, and the first day is represented as the average value of the time baseline of the same type of engineering as the to-be-monitored engineering. The first data is screened according to the screening standard, the first data is represented as each piece of historical monitoring data corresponding to the periodicity of the first number of days, the historical monitoring data is represented as a SAR image, the SAR image is represented as an image photographed by each pixel point on the surface of the satellite pair engineering subspace with a first distance spatial baseline, and the emitted radar wavelength is a first wavelength and the time baseline is the first number of days, and the spatial baseline is represented as the distance between the geometric centers of any one set of two satellites used for photographing; The deformation phase corresponding to any SAR image is extracted, the deformation phase is converted into a deformation rate according to the InSAR technology, the deformation rate at each pixel point of the engineering subspace is traversed, the average value of the deformation rate at each pixel point is calculated, and the average value of the deformation rate at each pixel point is recorded as a first deformation rate.

[0023] In a specific implementation, the average value of the historical time baseline of the same type of engineering is used as the first number of days, human trial and error is avoided, the setting process is 100% data driven, the execution result deviation of different teams is less than 1 day, the average value can be automatically updated every quarter, an industry baseline database is formed, the monitoring scheme is self-adaptively optimized according to the regional climate and satellite formation evolution, the screening condition locks the first number of days plus or minus 1 day period pool, the utilization rate of historical SAR images is increased from 65% to 88%, the number of effective interference pairs is significantly increased, the spatial baseline (first distance) and wavelength (first wavelength) are screened, additional phase noise caused by mixing is eliminated, the measured phase standard deviation is reduced by 0.3 radian, the rate is calculated after all pixel points in the subspace are averaged, which is equivalent to the arithmetic mean of 50-200 virtual PS, the random error is reduced, the rate uncertainty is reduced from plus or minus 3 mm per first number of days to plus or minus 0.7 mm per first number of days, the average process suppresses local scatterer anomalies, the result is not sensitive to transient targets such as roof temporary metal plate construction fences, the stability of the engineering-level interpretation is improved, batch matching of historical images only needs one SQL query (time baseline = first number of days plus or minus 1 day), the data screening of 1000 scenes of a single engineering takes less than 30 seconds, the pixel-average rate algorithm has been encapsulated as a pygmtsar one-line call, and the overall S100 step takes less than 10 minutes to run, without human intervention, after the phase noise is reduced, the subspace-level annual rate error is reduced by 40%, acceleration deformation greater than 10 mm per first number of days can be found 15 to 30 days in advance, the rate format is automatically bound with the IFC subspace Xi number, which is convenient for writing into a BIM and FEM coupled model, and realizing the standardization of the whole life cycle of surveying, monitoring and operation.

[0024] The first operation includes marking the engineering subspace and setting a key engineering subspace according to the first deformation rate. The setting method of the first operation includes: The first value is set as a deformation rate threshold, any engineering subspace is selected, the first deformation rate corresponding to the engineering subspace is compared with the first value, when the first deformation rate is less than or equal to the first value, the first operation is set as first marking the engineering subspace, and when the first deformation rate is greater than the first value, the first operation is set as setting a key engineering subspace.

[0025] When the first operation is the first marking of the engineering subspace, the number of the corresponding engineering subspace is marked red, and the first day number is added after the number of the engineering subspace, and the first marking is represented as X i And the first day number, a first folder is created, and the first marking is stored in the first folder; When the first operation is setting a key engineering subspace, a second folder is created, the number of the corresponding engineering subspace and the corresponding second data backup are stored in the second folder, the second data represents each historical monitoring data of the key engineering subspace, and each engineering subspace in the second folder is set as a key engineering subspace.

[0026] In a specific implementation, the first value is used as a unique threshold, the system is automatically shunted into two levels of red marking and key backup, 100% scripting, 0 manual judgment, avoiding human standard drift, and the shunting time is less than 1s per subspace, and a million subspace projects can complete the first round of risk identification in 1 minute, the red marking and the first day number added after the number can be identified by an engineer at a glance, a field inspection table is automatically generated, reducing 30% of the office sorting time, the numbering rules are linked with subsequent reports and BIM color cards, and one-key positioning to the corresponding components of the three-dimensional model is supported.

[0027] The first change amount is set as a change gradient of the first day number, and the original time baseline of the key engineering subspace is first regulated according to the first change amount, that is, the first day number is first regulated, and the first regulation is represented as continuous reduction, and the reduced first day number is set as a new time baseline; Any new time baseline is selected, and the historical monitoring data is selected every interval of the new time baseline from a starting time point of the historical monitoring data, and the selected historical monitoring data is set as to-be-analyzed data; Each new time baseline is traversed to obtain to-be-analyzed data corresponding to each new time baseline.

[0028] According to the order of the new time baseline from large to small, the first deformation rate corresponding to the new time baseline is continuously obtained; Until the first deformation rate corresponding to the new time baseline is less than or equal to the first value, the continuous reduction of the first day number is stopped, and the regulated time baseline at this time is obtained, which is recorded as a key day number; The second mark of the key subspace is represented as the number of the key subspace and the key time baseline, and the second mark is represented as X i And the key time baseline.

[0029] In the implementation, the time baseline is automatically decreased by the first change amount (decreasing gradient), and the system converges to the key days in 3-5 steps, without the need for expert experience, and the result deviation of different operators is less than 0.5 days. Compared with the scheme of a fixed experience value (such as 12 days), the image utilization rate is increased by 20%, the effective intervention is increased by 1.3-1.8 times, and the cycle is reduced, extracted, and compared until the rate is less than or equal to the first value, so that the key subspace still maintains the lowest detectable rate at the shortest time baseline, the theoretical monitoring sensitivity is improved by 40% (from 5 millimeters per first day to 3 millimeters per first day), and the key days are the best observation period of the subspace, which can be directly written into the observation task book to avoid over-sampling or under-sampling. During the decreasing process, only the key subspace is locally recalculated, and the low-risk area still uses the original long period. The overall CPU time is saved by 35%, and the key days usually fall within 6-24 days. Compared with the traditional 60-day scheme, the deformation mutation discovery time is averagely shortened by 18 days, which wins a golden window for rescue, and the second mark Xi and the key time baseline are written into the scheduling system in real time. The satellite task sheet can be automatically scheduled according to the key days to realize the monitoring and decision-making closed loop. The decreasing gradient can be set to a lower limit (greater than or equal to 6 days) to prevent infinite shortening from causing too low coherence. The algorithm is embedded with a coherence test. If the coherence degree γ is less than 0.3, the last period is automatically returned to ensure the reliability of the result. The value of γ ranges from 0 to 1, and the larger the value of γ, the more stable the calculation result of the current period.

[0030] The related data includes meteorological data and engineering subspace distribution parameters. The meteorological data includes annual average precipitation, daily average wind speed, annual average air humidity, annual temperature range, and annual average snow depth. The engineering subspace distribution parameters include compressible layer thickness, fill thickness, distance to water source, ground slope, daily load of building, groundwater level depth, and vegetation coverage.

[0031] The method for performing the second analysis on the related data, the first mark, and the second mark to obtain the influence relationship of the meteorological data on the time baseline and the influence relationship of the engineering subspace distribution parameters on the time baseline includes: The average value of the first days corresponding to the first mark and the key days corresponding to the second mark is calculated, denoted as the first average value. The first average value is used as the dependent variable, and the meteorological data is used as the independent variable to perform multiple regression analysis, and a first multiple regression equation is obtained. The first multiple regression equation is denoted as the influence relationship of the meteorological data on the time baseline. A first difference value of the first day corresponding to the first mark and the key day corresponding to the second mark is calculated, a multivariate regression analysis is performed with the first difference value as the dependent variable and the engineering subspace distribution parameter as the independent variable, and a second multivariate regression equation is obtained, which is denoted as the influence relationship of the engineering subspace distribution parameter on the time baseline; By inputting the meteorological data into the influence relationship of the meteorological data on the time baseline, the first average value of the new project of the same type as the monitored project is obtained, and the corresponding key day is inversely calculated according to the first day and the first average value of the new project. A first difference value of the first day and the key day corresponding to the new project is calculated, and the time baseline of each engineering subspace corresponding to the new project is obtained by inputting the corresponding first difference value into the influence relationship of the engineering subspace distribution parameter on the time baseline.

[0032] In the specific implementation, only meteorological five parameters and seven types of distribution parameters need to be input, and the first average value and the key day can be output within 1 second, without the need to run the complete InSAR process again, and the design efficiency is improved by 20 times. For new projects, satellite shooting plans can be determined 3-6 months in advance to avoid resource waste caused by shooting after calculation. The first multivariate regression equation gives explicit coefficients such as 1.2 days shortened for each 100 millimeters of annual average rainfall to the first average value, providing a scientific basis for emergency encryption observation in extreme climate years. The second multivariate regression equation reveals the rule that the first difference value is expanded by 0.7 days for each 10 meters of compressible layer thickness, which can be directly used for rapid recalculation in the case of sudden change of geological conditions.

[0033] The present application ensures that the deformation gradient in each calculation unit is less than 3 millimeters per first day through subspace and sensitivity secondary subdivision, reduces the standard deviation of the measured rate, reduces the atmospheric phase residual after introducing the meteorological and time baseline coupling model, compresses the annual rate error, and outputs the meteorological and time baseline and the distribution parameter and the time baseline double model, which can be directly embedded in the digital twin platform to realize the data, model and decision closed loop, provide an interpretable sensitive factor ranking for the operation and maintenance unit, assist in formulating targeted reinforcement, drainage or loading schemes, reduce operation and maintenance risks, the method is applicable to BIM, point cloud and grid three kinds of data sources, covers various engineering types such as dams, fills, bridges, landslides and subway tunnels, and the meteorological and geotechnical parameter table and the algorithm module are loosely coupled, which can be directly promoted to different climate zones and geological conditions by updating the parameter library without modifying the core code.

[0034] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-usable storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other storage medium(s) that can be used to carry or store desired computer program code in the form of instructions or data structures and that can be accessed by a computer. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through the based on any such medium, transactional medium, or physical medium. Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0035] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A method for monitoring engineering deformation based on big data, characterized in that, The method comprises the following steps: Step S100, selecting any engineering subspace, setting a screening standard, screening first data according to the screening standard, analyzing the first data to obtain a first deformation rate, performing a first operation according to the first deformation rate, and marking the first engineering subspace; Step S200, in response to the first operation, setting a key subspace, performing a first control on the time baseline of the key subspace, and marking the key subspace according to the first deformation rate after the first control; Step S300, performing a second analysis on the related data, the first mark and the second mark to obtain the influence relationship of the weather data on the time baseline and the influence relationship of the engineering subspace distribution parameter on the time baseline.

2. The big data based engineering deformation monitoring method of claim 1, wherein: Before setting the screening criteria, the to-be-monitored project is segmented, and the segmentation includes semantic segmentation, parameter segmentation, obtaining a project subspace and automatically numbering, and outputting the project subspace and the number thereof, wherein the number of the project subspace is represented as X i , i is a natural number; The semantic segmentation is performed on the three-dimensional model of the monitored engineering by using an open source tool and a classification manager, and the semantic representation is the name of the component of the engineering. The IFC is opened, the classification option is clicked, the independent model is created, and N independent objects are obtained; The parameter segmentation comprises setting the thickness mutation of the compressible layer to 2 meters as a first segmentation condition, setting the slope threshold to 10 degrees as a second segmentation condition, setting the minimum point number to 1000 as a third segmentation condition, segmenting the N independent objects, and obtaining M independent objects; According to the sequence of the segmentation software processing, the M independent objects are automatically numbered, and the M independent objects are recorded as engineering subspaces, and the numbers of the M independent objects are recorded as the numbers of the engineering subspaces.

3. The big data based engineering deformation monitoring method of claim 2, wherein: After the monitored engineering is segmented, any engineering subspace is selected, and a screening standard is set. The screening standard is that the time baseline is the first day number, and the time baseline is represented as the interval time length of SAR detection. The first day number is obtained by the time baseline of the engineering of the same type as the monitored engineering, and the first day number is represented as the average value of the time baseline of the engineering of the same type as the monitored engineering; According to the screening standard, first data is screened, the first data is represented as each historical monitoring data corresponding to the periodicity of the first day number, the historical monitoring data is represented as a SAR image, the SAR image is represented as an image in which each pixel point on the surface of the engineering subspace is photographed by a satellite with a first distance spatial baseline, and the radar wavelength is a first wavelength and the time baseline is a first day number, and the spatial baseline is represented as the distance between the geometric centers of any one group of two satellites used for photographing; The deformation phase corresponding to any SAR image is extracted, the deformation phase is converted into a deformation rate according to the InSAR technology, the deformation rate at each pixel point of the engineering subspace is traversed, the average value of the deformation rate at each pixel point is calculated, and the average value of the deformation rate at each pixel point is recorded as the first deformation rate.

4. The big data based engineering deformation monitoring method of claim 3, wherein: According to the first deformation rate, a first operation is performed, which comprises marking the engineering subspace and setting a key engineering subspace; The setting method of the first operation comprises: The first value is set as a deformation rate threshold, any engineering subspace is selected, the first deformation rate corresponding to the engineering subspace is compared with the first value, when the first deformation rate is less than or equal to the first value, the first operation is set as marking the engineering subspace, and when the first deformation rate is greater than the first value, the first operation is set as setting a key engineering subspace.

5. The big data based engineering deformation monitoring method of claim 4, wherein: When the first operation is the first marking on the engineering subspace, the number of the corresponding engineering subspace is marked red, and the first day number is added after the number of the engineering subspace, and the first marking is represented as X i And the first day number, create a first folder, and store the first marking in the first folder; When the first operation is setting the key engineering subspace, a second folder is created, the number of the corresponding engineering subspace and the corresponding second data backup are stored in the second folder, the second data represents each historical monitoring data of the key engineering subspace, and each engineering subspace in the second folder is set as the key engineering subspace.

6. The big data based engineering deformation monitoring method of claim 5, wherein: The first change amount is set as a change gradient of the first days, and the original time baseline of the key engineering subspace is first regulated according to the first change amount, that is, the first days are first regulated, and the first regulation is represented as continuous reduction, and the reduced first days are continuously set as new time baselines; Any new time baseline is selected, and the historical monitoring data is selected every interval of the new time baseline from a starting time point of the historical monitoring data, and the selected historical monitoring data is set as to-be-analyzed data; Each new time baseline is traversed to obtain to-be-analyzed data corresponding to each new time baseline.

7. The big data based engineering deformation monitoring method of claim 6, wherein: In the order of the new time baselines from large to small, the first deformation rate corresponding to the new time baselines is continuously obtained; Until the first deformation rate corresponding to the new time baseline is less than or equal to the first value, the continuous reduction of the first days is stopped, and the regulated time baseline at this time is obtained and recorded as a key day; a second label for the key subspace, the second label being represented as a number for the key subspace and a key time baseline, the second label being represented as X i and the key time baseline.

8. The big data based engineering deformation monitoring method of claim 1, wherein: The related data include meteorological data and engineering subspace distribution parameters; The meteorological data include annual average precipitation, daily average wind speed, annual average air humidity, annual temperature range, and annual average snow depth; The engineering subspace distribution parameters include compressible layer thickness, fill thickness, distance from water source, ground slope, daily average load of building, groundwater level depth, and vegetation coverage.

9. The big data based engineering deformation monitoring method of claim 8, wherein: A method for performing second analysis on the related data, the first mark and the second mark to obtain an influence relationship of the meteorological data on the time baseline and an influence relationship of the engineering subspace distribution parameters on the time baseline includes: An average value of the first days corresponding to the first mark and the key days corresponding to the second mark is calculated and recorded as a first average value, the first average value is used as a dependent variable, the meteorological data are used as independent variables, multivariate regression analysis is performed, a first multivariate regression equation is obtained, and the first multivariate regression equation is recorded as the influence relationship of the meteorological data on the time baseline; A first difference value of the first days corresponding to the first mark and the key days corresponding to the second mark is calculated, the first difference value is used as a dependent variable, the engineering subspace distribution parameters are used as independent variables, multivariate regression analysis is performed, a second multivariate regression equation is obtained, and the second multivariate regression equation is recorded as the influence relationship of the engineering subspace distribution parameters on the time baseline. The first average value of the new project of the same type as the monitored project is obtained by inputting the meteorological data into the influence relationship of the meteorological data on the time baseline, and the corresponding key days are inversely calculated according to the first days and the first average value of the new project; The first difference value between the first days and the key days corresponding to the new project is calculated, and the time baseline of each engineering subspace corresponding to the new project is obtained by inputting the corresponding first difference value into the influence relationship of the engineering subspace distribution parameter on the time baseline.

10. A big data based engineering deformation monitoring system for performing the big data based engineering deformation monitoring method of claim 1, characterized in that, It comprises a marking module, an analysis module and a construction module; The marking module selects any engineering subspace, sets a screening standard, screens the first data according to the screening standard, analyzes the first data, obtains a first deformation rate, executes a first operation according to the first deformation rate, and marks the first engineering subspace; The analysis module responds to the first operation, sets a key subspace, performs a first regulation on the time baseline of the key subspace, and performs a second marking on the key subspace according to the first deformation rate after the first regulation; The construction module performs a second analysis on the related data, the first marking and the second marking, and obtains the influence relationship of the meteorological data on the time baseline and the influence relationship of the engineering subspace distribution parameter on the time baseline.

Images