CN113700334B - CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method - Google Patents

CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method Download PDF

Info

Publication number
CN113700334B
CN113700334B CN202111037650.XA CN202111037650A CN113700334B CN 113700334 B CN113700334 B CN 113700334B CN 202111037650 A CN202111037650 A CN 202111037650A CN 113700334 B CN113700334 B CN 113700334B
Authority
CN
China
Prior art keywords
tombstone
monitoring
cultural relic
deviation rectifying
setting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111037650.XA
Other languages
Chinese (zh)
Other versions
CN113700334A (en
Inventor
淳庆
林怡婕
张承文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN202111037650.XA priority Critical patent/CN113700334B/en
Publication of CN113700334A publication Critical patent/CN113700334A/en
Application granted granted Critical
Publication of CN113700334B publication Critical patent/CN113700334B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E04—BUILDING
    • E04G—SCAFFOLDING; FORMS; SHUTTERING; BUILDING IMPLEMENTS OR AIDS, OR THEIR USE; HANDLING BUILDING MATERIALS ON THE SITE; REPAIRING, BREAKING-UP OR OTHER WORK ON EXISTING BUILDINGS
    • E04G23/00—Working measures on existing buildings
    • E04G23/02—Repairing, e.g. filling cracks; Restoring; Altering; Enlarging
    • E—FIXED CONSTRUCTIONS
    • E04—BUILDING
    • E04G—SCAFFOLDING; FORMS; SHUTTERING; BUILDING IMPLEMENTS OR AIDS, OR THEIR USE; HANDLING BUILDING MATERIALS ON THE SITE; REPAIRING, BREAKING-UP OR OTHER WORK ON EXISTING BUILDINGS
    • E04G23/00—Working measures on existing buildings
    • E04G23/04—Propping of endangered or damaged buildings or building parts, e.g. with respect to air-raid action
    • E—FIXED CONSTRUCTIONS
    • E04—BUILDING
    • E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
    • E04H13/00—Monuments; Tombs; Burial vaults; Columbaria
    • E04H13/003—Funeral monuments, grave sites curbing or markers not making part of vaults
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Architecture (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Structural Engineering (AREA)
  • Civil Engineering (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • Mechanical Engineering (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a CNN-based real-time monitoring method for correcting and reinforcing inclined tombstone cultural relics, which comprises the following steps of: s1, arranging a temporary protection support; s2, scanning the point cloud and performing data processing; s3, setting a crack identification module; s4, setting a gradient identification module; s5, setting a settlement amount identification module; s6, setting a strain identification module; s7, early warning and evaluation; and S8, safely correcting deviation. According to the invention, through the accurate point cloud data obtained by real-time scanning, the monitoring module monitors the change of the inclination rate in the deviation rectifying and reinforcing process and the possible crack damage, settlement damage and strain damage, so that the problems of errors and construction safety caused by a manual monitoring mode and a semi-manual semi-mechanical operation mode are avoided, and the deviation rectifying accuracy, the monitoring efficiency and the structural safety are improved. Under the condition of not causing secondary damage to the tombstone cultural relic body, the safety, effectiveness and feasibility of the correction and reinforcement process of the fragile tombstone cultural relic are ensured in an informatization monitoring mode.

Description

CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method
Technical Field
The invention belongs to the field of ancient building preservation and repair, and particularly relates to a CNN-based inclined tombstone cultural relic deviation rectification and reinforcement real-time monitoring method.
Background
The stone inscription heritage is an important component in the traditional building heritage, and the cultural results of the makers who develop society and accumulate in the times are gathered, but because most of the existing stone inscription heritage is stored in the open air, the conventional stone inscription heritage is high in volume and high in aspect ratio, is easily influenced by external factors such as foundation settlement, earthquake damage, artificial damage, plant breeding and the like, and even lacks protective measures such as fences or glass shielding and the like, the stone inscription heritage is always damaged obliquely to different degrees, and some inscriptions collapse. And the history of the stone inscription is hundreds of years or even thousands of years, the material performance of the stone is degraded due to accumulated damage, more potential safety hazards exist in the deviation rectifying process, once new cracks are generated due to improper deviation rectifying measures, the stone is easy to cause brittle failure, and the risk of damage exists. In the current process of rectifying and reinforcing the inscription stone cultural relics, the current rectifying technology mainly carries out real-time monitoring in modes of manual measurement or installation of a sensor and a cable on a cultural relic body, and the problems that the precision is limited, the potential damage characteristics of the cultural relic body are difficult to detect, and the installation of the sensor can cause secondary damage to the cultural relic body exist, so that a more intelligent, efficient and reasonable monitoring mode is needed to ensure that the inscription stone cultural relics are rectified and reinforced in a safe state.
The Convolutional Neural Networks (CNN) are feed forward Neural Networks (feed forward Neural Networks) including convolution calculation and having a deep structure, and are one of representative algorithms for deep learning (deep learning), and damage identification and detection based on the CNN technology has the characteristics of strong environmental adaptability, small interference influence and high identification accuracy.
Aiming at the problems, a CNN-based real-time monitoring method for correcting and reinforcing the inclined tombstone cultural relic is designed.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a CNN-based inclined tombstone cultural relic deviation rectification and reinforcement real-time monitoring method, which ensures the safety, effectiveness and feasibility of the deviation rectification and reinforcement process of the damageable tombstone cultural relic through an intelligent informatization real-time monitoring mode with high efficiency, high recognition degree and high precision under the condition of not causing secondary damage to a tombstone cultural relic body.
The purpose of the invention can be realized by the following technical scheme:
a CNN-based real-time monitoring method for correcting and reinforcing inclined tombstone cultural relics comprises the following steps:
s1, arranging a temporary protection support;
s2, scanning the point cloud and performing data processing;
s3, setting a crack identification module;
s4, setting a gradient identification module;
s5, setting a settlement amount identification module;
s6, setting a strain identification module;
s7, early warning and evaluation;
and S8, safely correcting deviation.
The S1 specifically includes: before deviation rectification construction, a steel frame temporary supporting device is arranged on the inclined historical relic, and the joint of the temporary supporting device and the inclined stele stone historical relic is connected and supported by adopting a flexible foam filling agent.
The S2 specifically includes: scanning the inclined stone cultural relics by a three-dimensional laser scanner, collecting initial point cloud data of the inclined stone cultural relics and the surrounding environment thereof, setting a three-dimensional rectangular coordinate system vertical to the horizontal ground in the collected initial point cloud data, respectively measuring the inclination angle between each vertical face of the inclined stone cultural relics and the horizontal ground by taking a certain geometric corner point on the ground of the inclined stone cultural relics as a coordinate origin, and preprocessing the point cloud data and amplifying the data by taking the measured minimum acute angle direction as a main inclination direction.
The S7 specifically includes: according to the current situation of the inscription stone cultural relics, corresponding early warning evaluation indexes of a tilt rate identification module, a settlement amount identification module and a strain identification module in the inclined inscription stone cultural relic correction real-time monitoring system are set.
Further, the S3 specifically includes: calibrating the crack characteristics of the surface of the stone historical relic of the preprocessed inclined stone historical relic point cloud data, constructing a sample database according to the calibrated image, dividing a training set and a verification set, identifying the crack characteristics of the stone historical relic on a test set based on an fast-R-CNN multi-target detection algorithm, training and updating a neural network, obtaining an optimal algorithm model for identifying the cracks of the stone historical relic according to the data of the verification set, and identifying and monitoring whether the crack width expands in the deviation rectifying process and whether the historical relic generates new cracks in the deviation rectifying process through the optimal algorithm model.
Further, the S4 specifically includes: the method comprises the steps of selecting a geometric surface perpendicular to the ground in the main inclination direction of the inclined stone monument cultural relic, setting a plurality of groups of inclination rate monitoring virtual target points, setting a twin network of an optimal algorithm model, learning preset inclination rate monitoring virtual target points by adopting the twin network and updating the model, so that the inclination rate monitoring virtual target points can be effectively identified, and the real-time inclination rate in the rectification reinforcement process is monitored through the geometric relationship among the inclination rate monitoring virtual target points.
Further, the real-time inclination rate in the rectification and reinforcement process in the step S4The operation process is as follows: setting a tilt rate virtual target point A on a vertical plane of the main tilt direction of the tilted stone monument cultural relic1(x1，y1，z1) T before the beginning of correction0The time is the coordinate (0, 0, 0), and the coordinate (x) on the same vertical plane is selected2，y2，z2) Targeting point A of2The rate of tilt kA1，A2Main tilt direction coordinate difference/(z)2-z1) Measured tilt k before deviation correction0Then t is1、t2，t3…tnThe real-time tilt rate of the time is k1、k2，k3…kn。
Further, in the tilt rate recognition module of S4, if the tombstone cultural relic is an irregular shape or the surface vertical to the ground is an upward gradually-divided shape, a regular shape for auxiliary observation is simultaneously established in the process of point cloud data preprocessing, and a tilt rate observation target point is set in the virtual shape.
Further, the S5 specifically includes: selecting a horizontal surface of the inclined stone monument cultural relic close to the ground and a vertical surface of the stone monument cultural relic, setting a plurality of groups of sedimentation amount monitoring virtual target points according to the twin network, and monitoring the sedimentation amount and the sedimentation rate of a soil body in the deviation rectifying process of the inclined stone monument cultural relic, the differential sedimentation rate of adjacent corner points of the cultural relic and the later sedimentation amount of the stone monument cultural relic after the deviation rectifying is finished through the vertical displacement values of the sedimentation amount monitoring virtual target points in different time differences.
Further, the S6 specifically includes: selecting a joint of the temporary supporting device and the tombstone cultural relic, setting a plurality of groups of strain monitoring virtual target points according to the twin network, converting strain data by measuring the displacement of the strain monitoring virtual target points on the surface of the temporary supporting device in the deviation rectifying process, selecting any one component on the temporary supporting device, and t before the deviation rectifying begins0At any moment, two adjacent strain monitoring virtual target points B in any area are set1(a0，b0，c0) And B2(c0，d0，f0)，t1Time B1The coordinates are (a1，b1，c1)，B2The coordinates are (c)1，d1，f1) The equal effect represented by the strain monitoring virtual target point (12) becomes:
Figure BDA0003247920440000041
by this value at t1、t2，t3…tnAnd monitoring whether the inclined tombstone cultural relics are suddenly damaged due to material degradation or external reasons in the deviation rectifying process by the change in time.
Further, the S8 specifically includes: setting the monitoring time point to t1、t2，t3…tnAnd scanning once every hour in the deviation rectifying process, transmitting the obtained high-precision point cloud data into a deviation rectifying real-time monitoring system of the inclined monument stone cultural relic, and monitoring crack damage, sedimentation amount, inclination rate and other possible strain damages which may be generated in the deviation rectifying process of the inclined monument stone cultural relic according to the real-time monitoring data so as to ensure that the correction of the monument stone cultural relic is carried out in a safe state.
The invention has the beneficial effects that:
1. according to the CNN-based tilt tombstone cultural relic deviation rectification and reinforcement real-time monitoring method, accurate point cloud data are obtained through real-time scanning, and the four monitoring modules monitor change of a tilt rate in the deviation rectification and reinforcement process and possible crack damage, settlement damage and strain damage, so that the problems of errors and construction safety caused by a traditional manual monitoring mode and a semi-manual semi-mechanical operation mode are solved, and the deviation rectification accuracy, the monitoring efficiency and the structural safety are greatly improved;
2. the CNN-based inclined tombstone cultural relic deviation rectification and reinforcement real-time monitoring method avoids the traditional method of sticking a sensor on the surface of the cultural relic or fixing the sensor in a mechanical mode, trains original point cloud data through a CNN-based convolutional neural network to obtain an optimal algorithm model, improves the accuracy of crack identification, avoids the damage of the tombstone cultural relic caused by the generation of new cracks and the expansion of old cracks in the deviation rectification process, simultaneously utilizes a twin network to learn and monitor virtual target points, guarantees the safety of the repair process from two aspects of visual identification and displacement identification, and ensures that the tombstone cultural relic cannot suffer secondary damage in the deviation rectification and reinforcement process;
3. according to the CNN-based real-time inclined tombstone cultural relic deviation rectification and reinforcement monitoring method, the point cloud scanning technology is used in the whole monitoring process, redundant monitoring auxiliary equipment is not adopted, the potential safety hazard problem caused by redundant cables is avoided, a recyclable temporary supporting and protecting device is erected outside the tombstone cultural relic before deviation rectification and reinforcement construction, the cultural relic cannot suddenly topple before construction through the interval between the environment-friendly flexible foam material filling agent buffering device and the tombstone cultural relic, and the requirements of environment protection and energy-saving construction are met while the safety of the cultural relic body is ensured.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of real-time monitoring during a rectification and reinforcement construction process of a tombstone cultural relic according to an embodiment of the present invention;
FIG. 2 is a top view of the rubble inscription correcting and reinforcing construction process for real-time monitoring;
fig. 3 is a flowchart of a method for correcting and reinforcing the inclined tombstone cultural relics in real time according to the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, 2 and 3, a CNN-based tilt tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method includes the following steps:
s1, arranging a temporary protection support
Before deviation rectifying construction, arranging a steel frame temporary supporting device 1 on an inclined cultural relic, and connecting and supporting the joint of the temporary supporting device 1 and the inclined tombstone cultural relic by adopting a flexible foam filling agent 2;
s2, scanning the point cloud and processing the data
Scanning the inclined stone historical relic by a three-dimensional laser scanner 3, acquiring initial point cloud data 4 of the inclined stone historical relic and the surrounding environment thereof, setting a three-dimensional rectangular coordinate system vertical to the horizontal ground in the acquired initial point cloud data 4, respectively measuring the inclination angle between each vertical surface and the horizontal ground of the inclined stone historical relic by taking a certain geometric corner point on the ground of the inclined stone historical relic as a coordinate origin, and taking the measured minimum acute angle direction as a main inclination direction, and then performing point cloud data preprocessing (denoising, simplifying, registering, hole filling and other processing) and data amplification (only performing some transformations on the original data without actually increasing the original data so as to create more data);
s3 setting crack recognition module
A crack identification module 6 of the inclined stone inscription cultural relic deviation correction real-time monitoring system 5 is arranged: calibrating the crack characteristics of the surface of the stone historical relic of the preprocessed inclined stone historical relic point cloud data, constructing a sample database according to a calibrated image, dividing a training set and a verification set, identifying the crack characteristics of the stone historical relic on a test set based on an fast-R-CNN multi-target detection algorithm, training and updating a neural network, obtaining an optimal algorithm model 13 for identifying the crack of the stone historical relic according to the data of the verification set, and identifying and monitoring whether the crack width expands in the deviation rectifying process and whether the historical relic generates a new crack in the deviation rectifying process through the optimal algorithm model 13;
s4 setting a tilt rate recognition module
The inclination rate identification module 7 of the inclined stone inscription cultural relic deviation correction real-time monitoring system 5 is arranged: selecting a geometric surface perpendicular to the ground in the main inclination direction of the inclined stone monument cultural relic, setting a plurality of groups of inclination rate monitoring virtual target points 8, setting a twin network 14 of an optimal algorithm model 13, learning the preset inclination rate monitoring virtual target points 8 by adopting the twin network 14 and updating the model, thereby effectively identifying the inclination rate monitoring virtual target points 8, monitoring the real-time inclination rate in the deviation rectifying and reinforcing process through the geometric relationship between the inclination rate monitoring virtual target points 8, and the operation process is as follows: setting a tilt rate virtual target point A on a vertical plane of the main tilt direction of the tilted stone monument cultural relic1(125.531, 1235.622, 1372.356) before the start of rectification t0The time is coordinate (0, 0, 0), a target point A2 with coordinates (125.733, 1235.622, 1872.356) on the same vertical plane is selected, and the slope k isA1，A2＝(x2-x1)/(z2-z1) The measured inclination rate k before deviation correction is approximately equal to 4.4 percent (127.733-125.531)/(1872.356-1372.356)0Then t is1、t2，t3…tnThe real-time tilt rate of the time is k1、k2，k3…kn；
S5 setting sedimentation amount identification module
A settlement identification module 9 of the inclined stone inscription correction real-time monitoring system 5 is arranged: selecting a horizontal surface of the inclined tombstone cultural relic close to the ground and a vertical surface of the tombstone cultural relic, setting a plurality of groups of sedimentation amount monitoring virtual target points 10 according to the twin network 14, and monitoring the sedimentation amount and the sedimentation rate of a soil body in the deviation rectifying process of the inclined tombstone cultural relic, the differential sedimentation rate of adjacent corner points of the cultural relic and the later sedimentation amount of the tombstone cultural relic after the deviation rectifying is finished through the vertical displacement values of the sedimentation amount monitoring virtual target points 10 in different time differences;
s6 setting strain identification module
The strain identification module 11 of the inclined stone inscription cultural relic deviation correction real-time monitoring system 5 is arranged: selecting the joint of the temporary supporting device and the monument cultural relic, setting a plurality of groups of strain monitoring virtual target points 12 according to the twin network 14, and measuring the strain data through the temporary supporting deviceThe displacement of the strain monitoring virtual target point 12 on the surface of the device 1 generated in the deviation rectifying process is converted, a certain component on the temporary supporting device 1 is selected, and t is carried out before the deviation rectifying begins0At any moment, two near-distance strain monitoring virtual target points 12B in any 50mm multiplied by 50mm area are set1(12.131, 5.620, 22.511) and B2(15.152，7.960，22.359)，t1Time B1Coordinates (12.133, 5.625, 22.512), B2Coordinates (15.155, 7.962, 22.361), the equivalent strain represented by the strain monitoring virtual target point 12 is:
Figure BDA0003247920440000081
by this value at t1、t2，t3…tnThe change in time can monitor whether the inclined tombstone cultural relics generate sudden damage due to material degradation or external reasons in the deviation rectifying process;
s7, early warning evaluation
Setting corresponding early warning evaluation indexes of a tilt rate identification module 7, a settlement identification module 9 and a strain identification module 11 in the inclined tombstone cultural relic rectification real-time monitoring system 5 according to the current situation of the tombstone cultural relic;
s8, safety correction
Setting the monitoring time point to t1、t2，t3…tnAnd scanning once every hour in the deviation rectifying process, transmitting the obtained high-precision point cloud data into the inclined tombstone cultural relic deviation rectifying real-time monitoring system 5, and monitoring crack damage, settlement amount, inclination rate and other possible strain damage which may be generated in the deviation rectifying process of the inclined tombstone cultural relic according to the real-time monitoring data so as to ensure that the tombstone cultural relic is rectified in a safe state.
It should be noted that in the S4, if the inclined stone historical relic is an irregular shape or a shape gradually converging upward from the surface perpendicular to the ground, a regular shape for auxiliary observation is simultaneously established during the process of point cloud data preprocessing, and an inclination observation target point is set in the virtual shape in the inclined stone historical relic identification module 7.
The monitoring method has the functions of secondary development, correction of accurate identification range according to instrument precision and reutilization.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.

Claims (1)

1. A CNN-based real-time monitoring method for correcting and reinforcing inclined tombstone cultural relics is characterized by comprising the following steps:
s1, arranging a temporary protection support;
s2, scanning the point cloud and performing data processing;
s3, setting a crack identification module;
s4, setting a gradient identification module;
s5, setting a settlement amount identification module;
s6, setting a strain identification module;
s7, early warning and evaluation;
s8, safely correcting deviation;
the S1 specifically includes: before deviation rectifying construction, arranging a steel frame temporary supporting device (1) on an inclined cultural relic, and connecting and supporting the joint of the temporary supporting device (1) and the inclined tombstone cultural relic by adopting a flexible foam filling agent (2);
the S2 specifically includes: scanning the inclined stone historical relic by a three-dimensional laser scanner (3), acquiring initial point cloud data (4) of the inclined stone historical relic and the surrounding environment thereof, setting a three-dimensional rectangular coordinate system vertical to the horizontal ground in the acquired initial point cloud data (4), respectively measuring the inclination angle between each vertical surface of the inclined stone historical relic and the horizontal ground by taking a certain geometric corner point on the ground of the inclined stone historical relic as a coordinate origin, and preprocessing point cloud data and amplifying data by taking the measured minimum acute angle direction as a main inclination direction;
the S7 specifically includes: according to the current situation of the inscription stone cultural relics, setting corresponding early warning evaluation indexes of a tilt rate identification module (7), a settlement amount identification module (9) and a strain identification module (11) in the inclined inscription stone cultural relic rectification real-time monitoring system (5);
the S3 specifically includes: calibrating the crack characteristics of the surface of the stone historical relic of the preprocessed inclined stone historical relic point cloud data, constructing a sample database according to a calibrated image, dividing a training set and a verification set, identifying the crack characteristics of the stone historical relic on a test set based on an fast-R-CNN multi-target detection algorithm, training and updating a neural network, obtaining an optimal algorithm model (13) for identifying the crack of the stone historical relic according to the data of the verification set, and identifying and monitoring whether the crack width expands in the deviation rectifying process and whether the historical relic generates a new crack in the deviation rectifying process through the optimal algorithm model (13);
the S4 specifically includes: selecting a geometric surface vertical to the ground in the main inclination direction of the inclined stone monument cultural relic, setting a plurality of groups of inclination rate monitoring virtual target points (8), setting a twin network (14) of an optimal algorithm model (13), learning preset inclination rate monitoring virtual target points (8) by adopting the twin network (14) and updating the model, thereby effectively identifying the inclination rate monitoring virtual target points (8), and monitoring the real-time inclination rate in the rectification reinforcement process through the geometric relationship between the inclination rate monitoring virtual target points (8);
the operation process of the real-time inclination rate in the deviation rectifying and reinforcing process in the step S4 is as follows: on the inclined stone tabletThe vertical plane of the main inclined direction of the cultural relic is provided with an inclination rate virtual target point A1(x1，y1，z1) T before the beginning of correction0The time is the coordinate (0, 0, 0), and the coordinate (x) on the same vertical plane is selected2，y2，z2) Targeting point A of2The rate of tilt kA1，A2Difference in principal tilt direction coordinates/(z)2-z1) Measured tilt k before deviation correction0Then t is1、t2，t3…tnThe real-time tilt rate of the time is k1、k2，k3…kn；
In the S4 inclination rate recognition module (7), if the tombstone cultural relic is an irregular shape or the surface vertical to the ground is in an upward gradually-divided shape, a regular shape for auxiliary observation is simultaneously established in the point cloud data preprocessing process, and an inclination rate observation target point is arranged in the virtual shape;
the S5 specifically includes: selecting a horizontal surface of the inclined tombstone cultural relic close to the ground and a vertical surface of the tombstone cultural relic, setting a plurality of groups of sedimentation amount monitoring virtual target points (10) according to the twin network (14), and monitoring the sedimentation amount and the sedimentation rate of a soil body in the deviation rectifying process of the inclined tombstone cultural relic, the differential sedimentation rate of adjacent corner points of the cultural relic and the later sedimentation amount of the tombstone cultural relic after the deviation rectifying is finished through the vertical displacement numerical values of the sedimentation amount monitoring virtual target points (10) in different time differences;
the S6 specifically includes: selecting a joint of a temporary supporting device and a stone monument cultural relic, arranging a plurality of groups of strain monitoring virtual target points (12) according to a twin network (14), converting strain data by measuring the displacement of the strain monitoring virtual target points (12) on the surface of the temporary supporting device (1) in the deviation rectifying process, selecting any one component on the temporary supporting device (1), and t before the deviation rectifying begins0At any moment, two adjacent strain monitoring virtual target points (12) B in any area are set1(a0，b0，c0) And B2(c0，d0，f0)，t1Time B1The coordinate is (a)1，b1，c1)，B2The coordinate is (d)1，e1，f1) The equal effect represented by the strain monitoring virtual target point (12) becomes:
Figure FDA0003563402220000031
by this value at t1、t2，t3…tnMonitoring whether the inclined tombstone cultural relics generate sudden damage due to material degradation or external reasons in the deviation rectifying process by the change in time;
the S8 specifically includes: setting the monitoring time point to t1、t2，t3…tnAnd scanning is carried out once per hour in the deviation rectifying process, the obtained high-precision point cloud data is transmitted into a real-time deviation rectifying monitoring system (5) for the inclined tombstone cultural relic, and crack damage, sedimentation amount, inclination rate and other possible strain damage which may be generated in the deviation rectifying process of the inclined tombstone cultural relic are monitored according to the real-time monitoring data, so that the deviation rectifying of the tombstone cultural relic is ensured under the safe state.
CN202111037650.XA 2021-09-06 2021-09-06 CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method Active CN113700334B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111037650.XA CN113700334B (en) 2021-09-06 2021-09-06 CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111037650.XA CN113700334B (en) 2021-09-06 2021-09-06 CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method

Publications (2)

Publication Number Publication Date
CN113700334A CN113700334A (en) 2021-11-26
CN113700334B true CN113700334B (en) 2022-05-17

Family

ID=78660372

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111037650.XA Active CN113700334B (en) 2021-09-06 2021-09-06 CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method

Country Status (1)

Country Link
CN (1) CN113700334B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114092469B (en) * 2021-12-02 2022-08-26 四川大学 Method and device for determining repair area of blade and readable storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110424479A (en) * 2019-07-30 2019-11-08 中冶集团武汉勘察研究院有限公司 A kind of rectifying of leaned building system and method based on 3 D laser scanning
CN112761199A (en) * 2021-01-20 2021-05-07 江苏东南特种技术工程有限公司 Static pressure anchor rod pile and broken pile underpinning supporting device for high-rise deviation correction and monitoring method thereof

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110424479A (en) * 2019-07-30 2019-11-08 中冶集团武汉勘察研究院有限公司 A kind of rectifying of leaned building system and method based on 3 D laser scanning
CN112761199A (en) * 2021-01-20 2021-05-07 江苏东南特种技术工程有限公司 Static pressure anchor rod pile and broken pile underpinning supporting device for high-rise deviation correction and monitoring method thereof

Also Published As

Publication number Publication date
CN113700334A (en) 2021-11-26

Similar Documents

Publication Publication Date Title
CN108106801A (en) Bridge tunnel disease non-contact detection system and detection method
CN111578919B (en) Method for improving verticality detection precision of high-rise tower drum structure
CN107893437B (en) Large open caisson foundation construction real-time monitoring system based on remote wireless transmission technology
CN108105039B (en) A kind of deformation test device and application thereof that wind-driven generator tower is connect with basis
CN105674952B (en) Building settlement measuring device and method
CN109959343A (en) A kind of device and method deformed using laser monitoring super high-rise building
CN101915558B (en) Geometric linear detection method of bridge member
CN113124782B (en) Construction perpendicularity detection method based on point cloud tolerance self-adaption
CN113379712B (en) Steel bridge bolt disease detection method and system based on computer vision
CN110310021B (en) Site environment and monitoring point matching system for foundation pit monitoring and early warning
CN113700334B (en) CNN-based inclined tombstone cultural relic deviation rectifying and reinforcing real-time monitoring method
CN114541480B (en) Steel shell immersed tube assembly precision inspection method and system
CN108645360A (en) A kind of bridge monitoring methods
CN114332402B (en) Steel bridge simulation pre-assembly method integrating ground type and hand-held laser scanning
CN106813590B (en) External floating roof tank deformation detection method
CN110424479A (en) A kind of rectifying of leaned building system and method based on 3 D laser scanning
CN113865570B (en) Method for measuring verticality of steel structure round upright post
CN114396871B (en) Prefabricated pier column installation position posture monitoring method based on three-dimensional laser scanning
JP2003232631A (en) Ground deformation measuring system with optical fiber sensor
CN111609833A (en) Settlement observation method for high-rise building
Sigurdardottir Strain-based monitoring methods for beam-like structures
CN110243355A (en) A kind of method of short distance calibration laser plummet apparatus
CN108027949A (en) Rehabilitation plan formulates support system, method and program
CN106611087B (en) A kind of television tower prediction of earthquake calamity appraisal procedure
CN115436392A (en) Method for detecting and monitoring bridge pier column verticality and appearance quality defects in unmanned aerial vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant