CN115014230B - Two-dimensional plane structure deformation measurement method and system - Google Patents
Two-dimensional plane structure deformation measurement method and system Download PDFInfo
- Publication number
- CN115014230B CN115014230B CN202210730540.XA CN202210730540A CN115014230B CN 115014230 B CN115014230 B CN 115014230B CN 202210730540 A CN202210730540 A CN 202210730540A CN 115014230 B CN115014230 B CN 115014230B
- Authority
- CN
- China
- Prior art keywords
- strain
- displacement
- vector
- normalized
- training
- 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
Links
- 238000000691 measurement method Methods 0.000 title claims abstract description 10
- 238000006073 displacement reaction Methods 0.000 claims abstract description 140
- 238000005259 measurement Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 135
- 239000013598 vector Substances 0.000 claims description 92
- 238000012545 processing Methods 0.000 claims description 35
- 238000010606 normalization Methods 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000002146 bilateral effect Effects 0.000 claims description 4
- 238000004886 process control Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 230000007774 longterm Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013079 data visualisation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a two-dimensional plane structure deformation measurement method and a system, wherein the method comprises the following steps: acquiring real-time strain data of different positions of a two-dimensional planar structure to be detected through CCD cameras which are symmetrically arranged on a two-dimensional planar component arranged opposite to the two-dimensional planar structure to be detected; determining real-time displacement data corresponding to the real-time strain data according to a pre-established strain-displacement prediction model; and determining the real-time deformation condition of the two-dimensional plane structure to be detected according to the real-time displacement data. The invention is suitable for long-term monitoring of the two-dimensional plane structure to be measured, has stable measurement result and small error, and can not cause damage to the object to be measured; and moreover, the collection workload can be greatly reduced, the real-time data analysis efficiency is improved, the dangerous state can be reported in time, dangerous parts are locked, and the loss is reduced.
Description
Technical Field
The invention relates to the technical field of deformation measurement, in particular to a two-dimensional plane structure deformation measurement method and system.
Background
The two-dimensional planar structure may be deformed during use due to various factors. If the array surface and the structural frame of the large-scale radar antenna are sensitive to temperature load, the large-scale radar antenna can be deformed seriously under the conditions of temperature difference in summer and uneven solar radiation, and the accuracy of the radar is greatly influenced; the radar antenna array structure can generate random deformation to a certain extent under the influence of factors such as gravity, wind load, temperature and the like, and the structural deformation can have great influence on the overall detection precision of the radar; in addition, some structures adopt the material combination with different thermal expansion coefficients, the influence of temperature load is more obvious, the structure is easy to generate larger strain, and the structure is extremely easy to damage or even destroy.
Therefore, how to quickly and accurately detect the deformation of the two-dimensional planar structure in real time becomes a technical problem to be solved.
Disclosure of Invention
The invention aims to solve the technical problems existing in the prior art and provides a two-dimensional plane structure deformation measuring method and system.
In order to solve the technical problems, the invention provides a two-dimensional plane structure deformation measuring method, which comprises the following steps: acquiring real-time strain data of different positions of a two-dimensional planar structure to be detected through CCD cameras which are symmetrically arranged on a two-dimensional planar component arranged opposite to the two-dimensional planar structure to be detected; determining real-time displacement data corresponding to the real-time strain data according to a pre-established strain-displacement prediction model; and determining the real-time deformation condition of the two-dimensional plane structure to be detected according to the real-time displacement data.
The beneficial effects of the invention are as follows: according to the invention, real-time strain data of different positions of a two-dimensional plane structure to be detected are obtained through a CCD camera, and real-time displacement data corresponding to the real-time strain data are determined according to a pre-established strain-displacement prediction model; the CCD camera is used for measuring optically, so that electromagnetic interference influence caused by an electrical measuring method can be avoided, and the problems that an acquisition value generated by a mode of directly using a laser displacement sensor to measure and acquire displacement data for a long time is unstable, an acquisition error is large, and the laser displacement sensor irradiates for a long time to cause damage to a two-dimensional plane structure to be measured can be effectively solved; the invention is suitable for long-term monitoring of the two-dimensional plane structure to be measured, has stable measurement result and small error, and can not cause damage to the object to be measured; the measured strain data can be measured in a full-field, real-time and non-contact manner, the data acquisition is relatively easy, the acquisition workload can be greatly reduced, the real-time data analysis efficiency is improved, the predicted displacement result can report structural shape change conditions in real time, the dangerous state can be conveniently reported in time, dangerous parts are locked, and the loss is reduced.
On the basis of the technical scheme, the invention can be improved as follows.
Further, pre-establishing the strain-displacement prediction model includes: in a calibration state, acquiring an original training set of training samples including a strain vector and a displacement vector; normalizing the training samples in the original training set by using a strain vector to determine a first normalization coefficient, and scaling the displacement vector by using the first normalization coefficient to obtain a normalized training set; normalizing the test sample by a strain vector to determine a second normalized coefficient; calculating the distance between the normalized strain vector of the test sample and the normalized strain vector of each training sample in the normalized training set; sorting the distances from small to large, selecting training samples in a normalized training set corresponding to the first k groups of distances in the sorting result as preferred training samples, obtaining a preferred training set, and calculating the weight of the preferred training samples; and estimating the strain of the measurement sample to the corresponding displacement vector according to the second normalization coefficient, the weight of the preferable training sample and the displacement vector of the preferable training sample.
The adoption of the further scheme has the beneficial effects that based on the acquired displacement and strain parameters as a training set, a corresponding strain-displacement function relation is established, and the real-time deformation estimation research on the two-dimensional plane structure is realized. The corresponding displacement parameters can be obtained by reversible pushing by directly collecting strain data, so that the collection workload is greatly reduced, the real-time data analysis efficiency is improved, the dangerous state can be conveniently reported in time, the dangerous position is locked, and the loss is reduced.
Further, in the calibration state, acquiring an original training set including a strain vector and a displacement vector for the training sample includes:
Setting n strain acquisition points and m displacement acquisition points on a two-dimensional plane structure to be measured in a calibration state; m and n are positive integers;
Arranging a plurality of laser displacement sensors on a two-dimensional plane component which is arranged opposite to the two-dimensional plane structure to be detected in an array manner, and arranging at least two CCD cameras in bilateral symmetry;
Measuring by a plurality of laser displacement sensors to obtain a displacement vector d m×1, and obtaining a strain vector e 2n×1 by two CCD cameras;
l training samples are obtained through multiple measurements to form an original training set S, S= { E, D }, wherein E represents an input strain matrix E 2n×L and D represents an output displacement matrix D m×L.
The adoption of the further scheme has the beneficial effects that the in-plane parameter information can be quickly obtained by arranging the displacement measuring points and the strain measuring points on the two-dimensional plane, and the history database is built, so that the subsequent data analysis is convenient.
Further, the training samples in the original training set are normalized by a strain vector to determine a first normalization coefficient, and the displacement vector is scaled by the first normalization coefficient to obtain a normalized training set S *, where the calculation formula is as follows:
wherein a represents a first normalization coefficient, e 2n×1 is a strain vector of the training sample of the original training set, d m×1 is a displacement vector of the training sample of the original training set, and d * m×1 represents a displacement vector of the training sample of the normalization training set S *.
Further, the test sample is normalized by the strain vector to determine a second normalized coefficient, and the calculation formula is as follows:
Wherein b is a second normalized coefficient, and e 0 2n×1 is a strain vector of the test sample.
The adoption of the further scheme has the beneficial effects that after the strain and the displacement are normalized, the data information subjected to the preliminary processing is caused to be limited in a certain category, the negative effect caused by the data information of the peculiar sample is eliminated, the calculation convergence speed of a model algorithm can be improved, and the accuracy of the model is better improved.
Further, the euclidean distance r i of the normalized strain vector e 0* 2n×1 of the test sample and the normalized strain vector e i* 2n×1 of each training sample in the normalized training set S * is calculated, and r= { r i }, where i=1, 2, 3 … … I, I is less than or equal to 2n.
The further scheme has the advantages that the Euclidean distance measuring method is adopted, the method is simple and efficient, the calculated amount can be reduced, and the calculation speed of the model is improved.
Further, the weight of the preferred training sample is calculated according to the following calculation formula:
Wherein alpha j is the weight of the jth preferred training sample in the preferred training set, and r j is the normalized strain vector e 0* 2n×1 of the test sample and the normalized strain vector of the jth preferred training sample in the preferred training set Is a distance of (3).
The adoption of the further scheme has the beneficial effects that the model is convenient to correct better, the proportion effect of the data parameters in the model is highlighted, and the result is more accurate.
Further, the calculating formula is as follows, according to the second normalized coefficient, the weight of the preferable training sample and the displacement vector of the preferable training sample, and the displacement vector corresponding to the strain direction of the measurement sample is estimated:
Wherein d 0 m×1 is an estimated value of the displacement vector corresponding to the strain direction of the measurement sample, b is a second normalization coefficient, alpha j is the weight of the j-th preferred training sample in the preferred training set, Is the displacement vector of the preferred training sample.
The adoption of the further scheme has the beneficial effects that for the two-dimensional plane structure, the prediction of displacement parameters can be realized by only measuring the strain parameters, the deformation information of each part of the two-dimensional plane structure at different moments is obtained, the mechanical change state of the two-dimensional plane is mastered in real time, the alarm information is convenient to upload in time, the displacement parameters can be effectively provided for other precise parts needing deformation compensation, the precise compensation is realized, and the precision requirement is improved.
In order to solve the technical problem, the invention also provides a two-dimensional plane structure deformation measurement system, which comprises: a two-dimensional planar member and a process control device; two CCD cameras (charge coupled DEVICE CAMERA) which are arranged symmetrically left and right on the two-dimensional plane component; the CCD camera is used for acquiring real-time strain data of different positions of the two-dimensional planar structure to be detected; the processing control device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and is characterized in that the two-dimensional plane structure deformation measuring method is realized when the processor executes the program.
On the basis of the technical scheme, the invention can be improved as follows.
Further, in the calibration state, a plurality of laser displacement sensors are arranged on the two-dimensional plane component in an array manner, and displacement vectors are obtained through measurement of the plurality of laser displacement sensors; the device also comprises a display connected with the processing control device, wherein the display is used for receiving the estimated values of the strain and displacement of different positions of the two-dimensional plane structure to be detected at different moments, which are sent by the processing control device.
Additional aspects of the invention and advantages thereof will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart of a two-dimensional planar structure deformation measurement method according to an embodiment of the present invention;
FIG. 2 is a graph of a comparison analysis of deformation measurement data and real data of a two-dimensional planar structure in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a two-dimensional planar structure deformation measurement system according to an embodiment of the present invention.
Detailed Description
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
As shown in fig. 1, a two-dimensional planar structure deformation measurement method provided by an embodiment of the present invention includes:
S110, acquiring real-time strain data of different positions of a two-dimensional planar structure to be detected through CCD cameras which are symmetrically arranged on a two-dimensional planar component which is arranged opposite to the two-dimensional planar structure to be detected;
s120, determining real-time displacement data corresponding to the real-time strain data according to a pre-established strain-displacement prediction model;
S130, determining the real-time deformation condition of the two-dimensional plane structure to be detected according to the real-time displacement data.
According to the embodiment of the invention, real-time strain data of different positions of a two-dimensional plane structure to be detected are obtained through a CCD camera, and real-time displacement data corresponding to the real-time strain data are determined according to a pre-established strain-displacement prediction model; the CCD camera is used for measuring optically, so that electromagnetic interference influence caused by an electrical measuring method can be avoided, and the problems that an acquisition value generated by a mode of directly using a laser displacement sensor to measure and acquire displacement data for a long time is unstable, an acquisition error is large, and the laser displacement sensor irradiates for a long time to cause damage to a two-dimensional plane structure to be measured can be effectively solved; the invention is suitable for long-term monitoring of the two-dimensional plane structure to be measured, has stable measurement result and small error, and can not cause damage to the object to be measured; the measured strain data can be measured in a full-field, real-time and non-contact manner, the data acquisition is relatively easy, the acquisition workload can be greatly reduced, the real-time data analysis efficiency is improved, the predicted displacement result can report structural shape change conditions in real time, the dangerous state can be conveniently reported in time, dangerous parts are locked, and the loss is reduced.
Before the two-dimensional plane structure deformation measurement method is executed, the strain-displacement prediction model is firstly constructed, and the construction process comprises the following steps:
S101, under a calibration state, acquiring an original training set of a training sample comprising a strain vector and a displacement vector. Specifically, the method comprises the following steps:
s1011, setting n strain acquisition points and m displacement acquisition points on a two-dimensional plane structure to be measured in a calibration state; m and n are positive integers;
s1012, arranging a plurality of laser displacement sensors on a two-dimensional plane component which is arranged opposite to the two-dimensional plane structure to be detected in an array manner, and arranging at least two CCD cameras in bilateral symmetry;
S1013, measuring and obtaining displacement vectors d m×1 through a plurality of laser displacement sensors, and obtaining strain vectors e 2n×1 through two CCD cameras;
S1014, L training samples are obtained through multiple measurements to form an original training set S, S= { E, D }, wherein E represents an input strain matrix E 2n×L and D represents an output displacement matrix D m×L.
S102, normalizing the training samples in the original training set by using a strain vector to determine a first normalization coefficient, and scaling the displacement vector by using the first normalization coefficient to obtain a normalized training set S *; the calculation formula is as follows:
Wherein a represents a first normalization coefficient, e 2n×1 is a strain vector of the training sample in the original training set, d m×1 is a displacement vector of the training sample in the original training set, and d * m×1 represents a displacement vector of the training sample in the normalization training set S *;
S103, normalizing the test sample by a strain vector to determine a second normalized coefficient; the calculation formula is as follows:
Wherein b is a second normalized coefficient, and e 0 2n×1 is a strain vector of the test sample.
S104, calculating the distance r i between the normalized strain vector e 0* 2n×1 of the test sample and the normalized strain vector e i* 2n×1 of each training sample in the normalized training set S * (Euclidean distance is adopted in the embodiment of the invention); note r= { r i }, where i=1, 2, 3 … … I, i+.2n.
S105, sorting the distances from small to large, selecting training samples in a normalized training set corresponding to the first k groups of distances in the sorting result as preferred training samples, obtaining a preferred training set S' *, and calculating the weight of the preferred training samples; the calculation formula is as follows:
Wherein alpha j is the weight of the jth preferred training sample in the preferred training set, and r j is the normalized strain vector e 0* 2n×1 of the test sample and the normalized strain vector of the jth preferred training sample in the preferred training set Is a euclidean distance of (c).
S106, estimating a displacement vector corresponding to the strain direction of the measurement sample according to the second normalization coefficient, the weight of the preferable training sample and the displacement vector of the preferable training sample, wherein the calculation formula is as follows:
Wherein d 0 m×1 is an estimated value of the displacement vector corresponding to the strain direction of the measurement sample, b is a second normalization coefficient, alpha j is the weight of the j-th preferred training sample in the preferred training set, Is the displacement vector of the preferred training sample.
In the process of acquiring the training set, n points are arranged on the two-dimensional plane structure to be tested, strains in the x direction and the y direction are respectively acquired, m points are arranged on the two-dimensional plane structure, displacement of the m points is measured, and a strain vector e 2n×1 and a displacement vector d m×1 can be obtained through each measurement. Assuming that there are L training samples, the training set consists of an input strain matrix E 2n×L and an output displacement matrix D m×L, training set s= { E, D }.
In one embodiment, when the two-dimensional planar structure to be measured is a two-dimensional planar frame, the displacement measurement selects 12 measuring points, and the strain measurement selects 25 measuring points. The measured data obtain 57 groups of samples, the data are sent to a database module of the processing control device 1,1 group is used as a test set, the other groups are used as training sets, the feasibility of the method is verified, and the generalization capability of the algorithm is evaluated. The verification result is shown in fig. 2, the predicted result of the obtainable position is basically consistent with the actually measured displacement result, the maximum error is 2.2mm, the maximum mean square error rate is 0.45%, the RMS is far less than 0.5mm, and the index requirement is met.
Therefore, the real-time displacement and the strain of the planar frame structure in the actual use process can be obtained accurately, the two parameters are used as a historical database, and a model algorithm is obtained according to the historical database, so that the data support is provided for a deformation error compensation link in the data processing process through strain reverse pushing displacement, and the precision requirement and the structure reliability of the two-dimensional planar structure under complex environmental conditions are ensured.
The two-dimensional plane component may be a steel plate, an aluminum alloy plate, a plastic plate, or a plurality of plates in the same plane, which are distributed at intervals, the plurality of laser displacement sensors are distributed on the surface of the two-dimensional plane component, for example, 16 laser displacement sensors may be distributed on the surface of the two-dimensional plane component in an array manner of 4×4, 30 laser displacement sensors 3 may be distributed on the surface of the two-dimensional plane component in an array manner of 5×6, it is understood that the array manner of the laser displacement sensors may be adjusted according to the actual situation, for example, a more densely distributed laser displacement sensors may be set to measure the measurement signals of the deformation positions of the two-dimensional plane structure to be measured, and a more dispersedly distributed laser displacement sensor may be set to measure the measurement signals of the deformation positions of the two-dimensional plane structure to be measured. And two CCD cameras are symmetrically distributed on the surface of the two-dimensional plane component.
And the plurality of laser displacement sensors and the two CCD cameras collect measurement signals of different positions of the antenna array surface of the radar at different moments according to preset frequency and send the measurement signals to the processing control device. The preset frequency can be 10 times a second, 20 times a second, etc., and can also be set according to actual conditions.
As shown in fig. 3, an embodiment of the present invention further provides a two-dimensional planar structure deformation measurement system, including: a two-dimensional planar member 2 and a process control device 1; in actual measurement, two CCD cameras 4 are symmetrically arranged on the two-dimensional plane component 2; the camera 4 of the CCD is used for acquiring real-time strain data of different positions of the two-dimensional planar structure 5 to be detected; the processing control device 1 includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the two-dimensional plane structure deformation measurement method according to the above embodiment when executing the program. Determining real-time displacement data corresponding to the real-time strain data according to a pre-established strain-displacement prediction model; and determining the real-time deformation condition of the two-dimensional plane structure to be detected according to the real-time displacement data. In the embodiment of the invention, the two-dimensional planar component 2 is fixed by a bracket, and the bracket is used for supporting the two-dimensional planar component.
In the calibration state, a plurality of laser displacement sensors 3 are arranged on the two-dimensional plane component 2 in an array manner, two CCD cameras 4 are symmetrically arranged left and right, displacement vectors d m×1 of the two-dimensional plane structure are obtained through measurement of the plurality of laser displacement sensors, and strain vectors e 2n×1 of the two-dimensional plane laser are obtained through the CCD cameras.
The process control apparatus 1 includes a hardware system and a software system. The hardware system mainly collects, classifies and stores displacement and strain parameters; the software system is mainly used for carrying out model training based on the obtained database to obtain corresponding model parameters, and finally establishing a mathematical model to realize the development of real-time deformation estimation research on the two-dimensional planar structure.
The hardware system comprises: the device comprises a two-dimensional plane component 2, a plurality of laser displacement sensors 3, two CCD cameras 4 (charge coupled DEVICE CAMERA), a display 6, a processing control device 1 and the like, wherein the plurality of laser displacement sensors 3 are arranged on the two-dimensional plane component 2 in an array manner, and the two CCD cameras 4 are arranged on the two-dimensional plane component 2 in a bilateral symmetry manner. When the plurality of laser displacement sensors 3 and the two CCD cameras 4 are used for setting the two-dimensional plane component 2 relative to the two-dimensional plane structure 5 to be measured, measurement signals of different positions of the two-dimensional plane structure 5 to be measured at different moments are collected according to preset frequencies and sent to the processing control device 1.
The processing control device is used for 1 realizing the installation and operation of a software system, is responsible for data storage, monitoring and intelligent management, and the display 6 is used for displaying the real-time signals acquired by the plurality of laser displacement sensors 3 and the CCD cameras 4, the details of a user management interface (including signal visualization, alarm inquiry, visualization of signal processing results, parameter setting interface) and the like. The processing control device is internally provided with a plurality of software modules, so that unified management and maintenance are facilitated.
The software system comprises: the system comprises a database module, a data processing module, a data visualization module, an alarm management module, a user management module, a digital analog A/D conversion module, an aviation plug module, a chassis power interface module and the like.
The database module is used for classifying and storing the data, storing historical acquisition data and being used for subsequent data statistical analysis and data processing. Specifically, the method is used for respectively acquiring displacement parameters of a plurality of laser displacement sensors and strain parameters acquired by a CCD camera, and storing the displacement parameters and the strain parameters in a corresponding database in a classified manner as historical data for subsequent data analysis.
The data processing module is used for performing data processing analysis on the acquired time domain data, including but not limited to filtering, noise reduction, statistical analysis, fast Fourier transformation, principal component analysis, wavelet analysis, spectrum analysis, neural network classification and the like, and is used for further identifying and classifying signals.
Specifically, according to signals acquired by each laser displacement sensor and two CCD cameras at an initial moment, an initial value corresponding to each laser displacement sensor and initial images corresponding to the two CCD cameras are obtained; obtaining a real-time measurement value of each laser displacement sensor and each CCD camera at each time after the initial time according to the measurement value of each laser displacement sensor and each CCD camera at each time after the initial time; and obtaining the displacement and the strain of different positions of the two-dimensional plane structure to be measured at different moments according to the measured initial value and the real-time measured value at each moment after the initial moment.
The data visualization module is used for displaying real-time signals, data processing effects, monitoring state information, data statistical information and the like of each channel, so that measuring conditions, data statistical information, monitoring state effects and the like of each channel can be mastered in real time.
The alarm management module is used for uploading alarm information to the display interface to send out alarm information after the result obtained after the analysis and the processing of the data processing module exceeds a preset safety threshold, the alarm information records can be displayed in a form of a table, the alarm information records comprise alarm sending time, alarm reasons, severity and possible solutions, the module can be used for rapidly locking dangerous parts, feeding back the plane health state and evaluation of a structure to be detected, sending out alarms in time when faults and hidden danger occur, ensuring normal and reliable operation of equipment and reducing loss.
The user management module mainly comprises software authority management of the functions of each functional module of the software by a user, gives different authorities to each user, and can reduce misoperation behaviors caused by insufficient expert knowledge of the user. The users can be classified into three levels of operators, technicians and administrators, and the modification parameter authorities are different from low to high correspondingly, so that the system management is facilitated and misoperation is prevented.
The digital analog A/D conversion module is used for carrying out digital analog A/D conversion on signals measured by the sensor to obtain digital quantity signals corresponding to each measured signal one by one, and sending each digital quantity signal to the data processing module.
The processing control device also comprises a power supply module, and the power supply module is connected with the data processing module, the A/D conversion module and the interface and supplies power. The embodiment of the invention can not effectively improve the portability of the device through the independent power supply module.
The software system further comprises a corresponding software interface: the system mainly comprises a window interface, a signal processing method interface and an acquisition card interface. Through interfacing, a developer can conveniently and rapidly develop and update functional modules such as a signal processing method, data acquisition card management and the like.
The software system further comprises a strain-displacement measurement model, the model algorithm generation comprising: under the calibration state, obtaining strain-displacement relations under different working conditions to form a training set database; model training is carried out based on a training set database strain-displacement measurement model, and a prediction model after training is deployed into engineering; in an actual measurement state, strain data are collected in real time, corresponding displacement data are predicted through a trained model, and real-time deformation measurement of a two-dimensional plane is achieved.
In the process of acquiring the training set, n points are arranged on the two-dimensional plane structure to be tested, strains in the x direction and the y direction are respectively acquired, m points are arranged on the two-dimensional plane structure, displacement of the m points is measured, and a strain vector e 2n×1 and a displacement vector d m×1 can be obtained through each measurement. Assuming that there are L training samples, the training set consists of an input strain matrix E 2n×L and an output displacement matrix D m×L, training set s= { E, D }.
The main principle of estimating the displacement vector d 0 m×1 by testing the sample strain vector e 0 2n×1 in the embodiment of the invention is as follows:
1) Normalizing each training sample in the training set S by a strain vector, and amplifying or reducing the displacement vector by a strain vector normalization coefficient, namely, for each training sample Forming a normalized training set S *; the first normalization coefficient is recorded as
2) The test sample is normalized by strain vector |e 0* 2n×1 |=1, and the second normalized coefficient is recorded as
3) Calculating the distance r i between the normalized strain vector e 0* 2n×1 of the test sample and each training sample e i* 2n×1 in the normalized training set S *, and recording r= { r i }; the distance measurement has various forms, and the embodiment of the invention adopts Euclidean distance; wherein i=1, 2, 3 … … I, I is less than or equal to 2n;
4) Sorting the distances from small to large, and selecting training samples in the normalized training set corresponding to the first k groups of distances in the sorting result as preferred training samples to obtain a preferred training set S' *; and calculating the weight of the preferred training sample; the calculation formula is as follows:
5) And estimating a displacement vector corresponding to the strain direction of the measurement sample according to the second normalization coefficient, the weight of the preferable training sample and the displacement vector of the preferable training sample, wherein the calculation formula is as follows:
The two-dimensional plane structure deformation measurement system provided by the embodiment of the invention further comprises a display connected with the processing control device, wherein the display is used for receiving the estimated values of the strain and displacement of different positions of the two-dimensional plane structure to be measured at different moments, which are sent by the processing control device. According to the embodiment of the invention, strain values and displacement estimated values of different positions of the two-dimensional plane structure to be detected at different moments are displayed on the display, so that the user can visually check the strain values and the displacement estimated values conveniently.
In the embodiment of the invention, when the two-dimensional planar structure to be detected is an antenna array surface of a radar, a two-dimensional planar component is arranged relative to the antenna array surface of the radar, a plurality of laser displacement sensors and two CCD cameras are used for collecting measurement signals of different positions of the antenna array surface of the radar at different moments according to preset frequencies and sending the measurement signals to a processing control device, a database module arranged in the processing control device is used for storing the measurement signals of different moments collected by each laser displacement sensor and the two CCD cameras, and then the displacement and strain of the antenna array surface of the radar at different moments can be accurately obtained after analysis and processing by a data processing module in a processing control box, so that a database is established, and the database can be used as a basis for subsequent data analysis.
The two-dimensional plane structure to be measured is an antenna array surface of the radar, and can provide data support for an error compensation link in the data processing process according to the obtained real-time strain parameter and the displacement estimated value, so that the detection accuracy and the structural reliability of the antenna array surface of the radar to a target are ensured.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and units described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A two-dimensional planar structure deformation measurement method, characterized by comprising:
Acquiring real-time strain data of different positions of a two-dimensional planar structure to be detected through CCD cameras which are symmetrically arranged on a two-dimensional planar component arranged opposite to the two-dimensional planar structure to be detected;
Determining real-time displacement data corresponding to the real-time strain data according to a pre-established strain-displacement prediction model;
pre-building the strain-displacement prediction model includes:
in a calibration state, acquiring an original training set of training samples including a strain vector and a displacement vector; under the calibration state, acquiring an original training set of training samples including a strain vector and a displacement vector, including: setting n strain acquisition points and m displacement acquisition points on a two-dimensional plane structure to be measured in a calibration state; m and n are positive integers; arranging a plurality of laser displacement sensors on a two-dimensional plane component which is arranged opposite to the two-dimensional plane structure to be detected in an array manner, and arranging at least two CCD cameras in bilateral symmetry; measuring by a plurality of laser displacement sensors to obtain a displacement vector d m×1, and obtaining a strain vector e 2n×1 by two CCD cameras; obtaining L training samples through multiple measurements to form an original training set S, S= { E, D }, wherein E represents an input strain matrix E 2n×L and D represents an output displacement matrix D m×L;
Normalizing the training samples in the original training set by using a strain vector to determine a first normalization coefficient, and scaling the displacement vector by using the first normalization coefficient to obtain a normalized training set;
normalizing the test sample by a strain vector to determine a second normalized coefficient;
calculating the distance between the normalized strain vector of the test sample and the normalized strain vector of each training sample in the normalized training set;
sorting the distances from small to large, selecting training samples in a normalized training set corresponding to the first k groups of distances in the sorting result as preferred training samples, obtaining a preferred training set, and calculating the weight of the preferred training samples;
estimating a corresponding displacement vector of the strain direction of the measurement sample according to the second normalization coefficient, the weight of the preferable training sample and the displacement vector of the preferable training sample;
And determining the real-time deformation condition of the two-dimensional plane structure to be detected according to the real-time displacement data.
2. The method of claim 1, wherein the normalizing the training samples in the original training set with a strain vector to determine a first normalized coefficient, and scaling the displacement vector with the first normalized coefficient to obtain a normalized training set S *, where the calculation formula is as follows:
wherein a represents a first normalization coefficient, e 2n×1 is a strain vector of the training sample of the original training set, d m×1 is a displacement vector of the training sample of the original training set, and d * m×1 represents a displacement vector of the training sample of the normalization training set S *.
3. The method of claim 1, wherein normalizing the test sample with the strain vector determines a second normalized coefficient as follows:
Wherein b is a second normalized coefficient, and e 0 2n×1 is a strain vector of the test sample.
4. The method according to claim 1, wherein the euclidean distance r i of the test sample normalized strain vector e 0* 2n×1 from each training sample normalized strain vector e i* 2n×1 in the normalized training set S * is calculated, denoted r= { r i }, wherein I = 1, 2, 3 … … I, I is less than or equal to 2n.
5. The method of claim 1, wherein the calculating the weights of the preferred training samples is as follows:
Wherein alpha j is the weight of the jth preferred training sample in the preferred training set, and r j is the normalized strain vector e 0* 2n×1 of the test sample and the normalized strain vector of the jth preferred training sample in the preferred training set Is a distance of (3).
6. The method of claim 5, wherein the estimating the displacement vector for the strain direction of the measurement sample based on the second normalized coefficient, the weight of the preferred training sample, and the displacement vector of the preferred training sample is calculated as follows:
Wherein d 0 m×1 is an estimated value of the displacement vector corresponding to the strain direction of the measurement sample, b is a second normalization coefficient, alpha j is the weight of the j-th preferred training sample in the preferred training set, Is the displacement vector of the preferred training sample.
7. A two-dimensional planar structure deformation measurement system, comprising: a two-dimensional planar member and a process control device; two CCD cameras which are arranged symmetrically left and right on the two-dimensional plane component; the CCD camera is used for acquiring real-time strain data of different positions of the two-dimensional plane structure to be detected;
The processing control device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the two-dimensional planar structure deformation measurement method according to any one of claims 1 to 6.
8. The system according to claim 7, wherein in the calibration state, a plurality of laser displacement sensors are arrayed on the two-dimensional planar member, and displacement vectors are obtained by measurement of the plurality of laser displacement sensors; the device also comprises a display connected with the processing control device, wherein the display is used for receiving the estimated values of the strain and displacement of different positions of the two-dimensional plane structure to be detected at different moments, which are sent by the processing control device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210730540.XA CN115014230B (en) | 2022-06-24 | 2022-06-24 | Two-dimensional plane structure deformation measurement method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210730540.XA CN115014230B (en) | 2022-06-24 | 2022-06-24 | Two-dimensional plane structure deformation measurement method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115014230A CN115014230A (en) | 2022-09-06 |
| CN115014230B true CN115014230B (en) | 2024-10-25 |
Family
ID=83076120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210730540.XA Active CN115014230B (en) | 2022-06-24 | 2022-06-24 | Two-dimensional plane structure deformation measurement method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115014230B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118688771B (en) * | 2024-08-22 | 2024-10-22 | 天津光粒科技发展有限公司 | Laser ranging calibration method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108489413A (en) * | 2018-04-28 | 2018-09-04 | 华南理工大学 | A kind of concrete surface heterogeneous strain measuring system and method |
| CN109883344A (en) * | 2019-01-16 | 2019-06-14 | 上海海事大学 | A kind of detection method of marine anticorrosion coating surface strain and displacement |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111982001A (en) * | 2020-08-26 | 2020-11-24 | 北京无线电测量研究所 | Deformation measurement system and method |
| CN114370852B (en) * | 2021-12-15 | 2024-03-05 | 安徽理工大学 | Accurate evaluation method and system for working face well-ground joint test ground subsidence basin |
| CN114417537B (en) * | 2022-04-01 | 2022-06-17 | 中国工程物理研究院流体物理研究所 | Open type walking framework structure deformation field real-time measurement method, device and system |
| CN114417681B (en) * | 2022-04-01 | 2022-06-17 | 中国工程物理研究院流体物理研究所 | Two-dimensional structure deformation monitoring method and device based on dynamic decision and neural network |
-
2022
- 2022-06-24 CN CN202210730540.XA patent/CN115014230B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108489413A (en) * | 2018-04-28 | 2018-09-04 | 华南理工大学 | A kind of concrete surface heterogeneous strain measuring system and method |
| CN109883344A (en) * | 2019-01-16 | 2019-06-14 | 上海海事大学 | A kind of detection method of marine anticorrosion coating surface strain and displacement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115014230A (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108664990B (en) | Electricity stealing detection method and device based on comprehensive entropy method and density clustering method | |
| CN106198924B (en) | Precarious rock mass monitoring system and its methods of risk assessment based on adaptive frequency acquisition | |
| CN117007984B (en) | Dynamic monitoring method and system for operation faults of battery pack | |
| CN115014230B (en) | Two-dimensional plane structure deformation measurement method and system | |
| CN117471346A (en) | Method and system for determining remaining life and health status of retired battery module | |
| Carotenuto et al. | Online recording a PV module fingerprint | |
| CN116248176A (en) | Optical fiber state monitoring and early warning method, system, equipment and medium | |
| CN115986918A (en) | Intelligent monitoring system for power transmission line | |
| CN113283113B (en) | Solar cell array power generation current prediction model training method, abnormality detection method, device and medium | |
| KR101948850B1 (en) | Electrical Impedance DEVICE AND METHOD FOR Damage MONITORING in SELF-SENSING CONCRETE-BASED STRUCTUREs | |
| WO2022049552A8 (en) | Method and system for tracking, monitoring and predicting the health of a plant heritage | |
| CN113973403B (en) | Temperature-induced strain field redistribution intelligent sensing method based on structure discrete measurement point topology | |
| CN115684908A (en) | State monitoring method for power GIS equipment, storage medium and electronic device | |
| CN109032214A (en) | A kind of computer room security alerting system | |
| CN117422200B (en) | Intelligent monitoring and early warning method and system for power plant | |
| CN116388859B (en) | Optical fiber state monitoring data acquisition device, method, equipment and medium | |
| CN116879121B (en) | Air particulate matter concentration real-time monitoring system based on optical fiber sensing technology | |
| CN116318387B (en) | Optical fiber state online monitoring method, system, equipment and medium | |
| CN113960112B (en) | Power equipment defect judging method and system | |
| CN112504137B (en) | Multi-target digital image detection method based on cloud computing | |
| CN116718295B (en) | Remote automatic acquisition system for pressure gauge data | |
| TWI833549B (en) | Sunshine value estimation system | |
| CN118171217B (en) | Hydraulic engineering water level early warning method and system based on BIM technology | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN118445738B (en) | Atomizer temperature data analysis method and system |
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 |