CN116147548A - Nondestructive testing method and system for thickness of steel fiber RPC cover plate - Google Patents
Nondestructive testing method and system for thickness of steel fiber RPC cover plate Download PDFInfo
- Publication number
- CN116147548A CN116147548A CN202310421390.9A CN202310421390A CN116147548A CN 116147548 A CN116147548 A CN 116147548A CN 202310421390 A CN202310421390 A CN 202310421390A CN 116147548 A CN116147548 A CN 116147548A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- feature vector
- image
- image feature
- echo
- 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.)
- Granted
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 115
- 239000000835 fiber Substances 0.000 title claims abstract description 115
- 239000010959 steel Substances 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000009659 non-destructive testing Methods 0.000 title claims abstract description 37
- 239000013598 vector Substances 0.000 claims abstract description 340
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000000903 blocking effect Effects 0.000 claims abstract description 21
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000002604 ultrasonography Methods 0.000 claims description 106
- 238000009826 distribution Methods 0.000 claims description 95
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 84
- 238000013507 mapping Methods 0.000 claims description 82
- 230000005540 biological transmission Effects 0.000 claims description 48
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000007689 inspection Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 230000001066 destructive effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 abstract description 29
- 239000000463 material Substances 0.000 description 10
- 238000013527 convolutional neural network Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000005259 measurement Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000003860 storage Methods 0.000 description 5
- 238000009683 ultrasonic thickness measurement Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 230000001902 propagating effect Effects 0.000 description 3
- 239000004568 cement Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000000941 radioactive substance Substances 0.000 description 1
- 239000012779 reinforcing material Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B17/00—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations
- G01B17/02—Measuring arrangements characterised by the use of infrasonic, sonic or ultrasonic vibrations for measuring 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30132—Masonry; Concrete
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
A nondestructive testing method and system for the thickness of steel fiber RPC cover plate is disclosed. Firstly, carrying out gram angle and field transformation on an obtained ultrasonic emission signal and an obtained ultrasonic echo signal to obtain an ultrasonic emission gram angle and field image and an ultrasonic echo gram angle and field image, then carrying out image blocking processing on the ultrasonic emission gram angle and field image and the ultrasonic echo gram angle and field image, obtaining an ultrasonic emission image characteristic vector and an ultrasonic echo image characteristic vector through a ViT model containing an embedded layer, and finally, carrying out decoder on a differential characteristic vector obtained by calculating the ultrasonic emission image characteristic vector and the ultrasonic echo image characteristic vector to obtain a decoding value for representing a thickness value. Thus, nondestructive detection of the thickness of the steel fiber RPC cover plate can be realized.
Description
Technical Field
The present application relates to the field of intelligent detection, and more particularly, to a nondestructive detection method and system for steel fiber RPC cover plate thickness.
Background
Reactive Powder Concrete (RPC) is a cement-based material with excellent ultra-high strength, high durability, high toughness and volume stability developed by using conventional cement or the like. The RPC cover plate can effectively lighten the dead weight of the structure and reduce the thickness of the interface transition region. The RPC cover plate is very compact and has extremely low porosity, so that radioactive substances can be prevented from leaking from the inside, the corrosion of external aggressive media can be resisted, and the uniformity, the strength and the durability of the system are improved as a whole.
The steel fiber RPC cover plate is prepared by adding steel fibers into the preparation material of the RPC cover plate to be used as a reinforcing material so as to optimize the strength performance of the RPC cover plate, such as the compressive strength, the flexural tensile strength and the like of the RPC cover plate. At present, in the practical application of the steel fiber RPC cover plate, the thickness detection of the steel fiber RPC cover plate is particularly important. However, the existing steel fiber RPC cover plate thickness detection is mechanical thickness measurement, manual operation is needed, and scratches are caused on the surface of the steel fiber RPC cover plate.
Thus, a more optimal non-destructive inspection scheme for steel fiber RPC cover plate thickness is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides a nondestructive testing method and system for the thickness of a steel fiber RPC cover plate. Firstly, carrying out gram angle and field transformation on an obtained ultrasonic emission signal and an obtained ultrasonic echo signal to obtain an ultrasonic emission gram angle and field image and an ultrasonic echo gram angle and field image, then carrying out image blocking processing on the ultrasonic emission gram angle and field image and the ultrasonic echo gram angle and field image, obtaining an ultrasonic emission image characteristic vector and an ultrasonic echo image characteristic vector through a ViT model containing an embedded layer, and finally, carrying out decoder on a differential characteristic vector obtained by calculating the ultrasonic emission image characteristic vector and the ultrasonic echo image characteristic vector to obtain a decoding value for representing a thickness value. Thus, nondestructive detection of the thickness of the steel fiber RPC cover plate can be realized.
According to one aspect of the present application, there is provided a non-destructive inspection method for steel fiber RPC cover plate thickness, comprising:
acquiring an ultrasonic emission signal and an ultrasonic echo signal;
carrying out gram angle and field transformation on the ultrasonic wave emission signal and the ultrasonic wave echo signal to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image;
performing image blocking processing on the ultrasonic emission gram angle and the field image and the ultrasonic echo gram angle and the field image, and then obtaining an ultrasonic emission image feature vector and an ultrasonic echo image feature vector through a ViT model containing an embedded layer;
calculating a differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector; and
the differential feature vector is passed through a decoder to obtain decoded values, which are used to represent thickness values.
In the above nondestructive testing method for steel fiber RPC cover plate thickness, the steps of performing image blocking processing on the ultrasonic emission gram angle and the field image and the ultrasonic echo gram angle and the field image to obtain an ultrasonic emission image feature vector and an ultrasonic echo image feature vector by using a ViT model containing an embedded layer include:
Respectively carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks;
respectively inputting the sequence of the ultrasonic emission image blocks and the sequence of the ultrasonic echo image blocks into the embedded layer to obtain a sequence of ultrasonic emission image block feature vectors and a sequence of ultrasonic echo image block feature vectors; and
and respectively passing the sequence of the ultrasonic emission image block characteristic vectors and the sequence of the ultrasonic echo image block characteristic vectors through the ViT model to obtain the ultrasonic emission image characteristic vectors and the ultrasonic echo image characteristic vectors.
In the nondestructive testing method for the thickness of the steel fiber RPC cover plate, calculating the differential characteristic vector between the ultrasonic emission image characteristic vector and the ultrasonic echo image characteristic vector comprises the following steps:
calculating a correlation-probability density distribution affine mapping factor between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor;
Weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector by taking the affine mapping factor of the first association-probability density distribution and the affine mapping factor of the second association-probability density distribution as weights so as to obtain an optimized ultrasonic emission image feature vector and an optimized ultrasonic echo image feature vector; and
and calculating the difference according to positions between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector.
In the above-mentioned nondestructive testing method for steel fiber RPC cover plate thickness, calculating a correlation-probability density distribution affine mapping factor between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor, comprising:
calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor;
Wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector, +.>
A correlation matrix obtained for a position-by-position correlation between the ultrasound transmit image feature vector and the ultrasound echo image feature vector,>
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix representing the calculation of a natural exponential function value raised to a power by a characteristic value at each position in the matrix,/v>
Affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor.
In the above nondestructive testing method for steel fiber RPC cover plate thickness, calculating the difference by position between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector includes:
calculating the differential feature vector between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector by using the following differential formula;
Wherein, the difference formula is:
wherein ,
representing the optimized ultrasound emission image feature vector, and (2)>
Representing the optimized ultrasound echo image feature vector, < >>
Representing the differential eigenvector,>
representing the difference by location.
In the nondestructive testing method for the thickness of the steel fiber RPC cover plate, the differential feature vector is passed through a decoder to obtain a decoded value, and the decoded value is used for representing the thickness value, and the method comprises the following steps:
performing decoding regression on the differential feature vector with a decoding formula using a plurality of fully connected layers of the decoder to obtain the decoded value, wherein the decoding formula is:
, wherein />
Is the differential eigenvector,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
According to another aspect of the present application, there is provided a non-destructive inspection system for steel fiber RPC cover plate thickness, comprising:
the signal acquisition module is used for acquiring an ultrasonic emission signal and an ultrasonic echo signal;
the gram angle and field conversion module is used for carrying out gram angle and field conversion on the ultrasonic wave emission signal and the ultrasonic wave echo signal so as to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image;
The encoding module is used for carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image, and obtaining ultrasonic wave emission image feature vectors and ultrasonic wave echo image feature vectors through a ViT model containing an embedded layer;
the difference calculation module is used for calculating a difference feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector;
and a decoding module for passing the differential feature vector through a decoder to obtain a decoded value, the decoded value being indicative of a thickness value.
In the nondestructive testing system for the thickness of the steel fiber RPC cover plate, the coding module is used for:
respectively carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks;
respectively inputting the sequence of the ultrasonic emission image blocks and the sequence of the ultrasonic echo image blocks into the embedded layer to obtain a sequence of ultrasonic emission image block feature vectors and a sequence of ultrasonic echo image block feature vectors;
And passing the sequence of ultrasonic emission image block feature vectors and the sequence of ultrasonic echo image block feature vectors through the ViT model to obtain the ultrasonic emission image feature vectors and the ultrasonic echo image feature vectors, respectively.
In the nondestructive testing system for steel fiber RPC cover plate thickness, the differential computing module comprises:
a correlation-probability density distribution affine mapping factor calculating unit for calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor;
the weighting optimization unit is used for weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector by taking the affine mapping factors of the first association-probability density distribution and the affine mapping factors of the second association-probability density distribution as weights so as to obtain an optimized ultrasonic emission image feature vector and an optimized ultrasonic echo image feature vector;
and a per-position difference unit for calculating a per-position difference between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector.
In the nondestructive testing system for steel fiber RPC cover plate thickness, the correlation-probability density distribution affine mapping factor calculating unit is used for:
calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor;
wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector, +.>
Transmitting image features for the ultrasound wavesA correlation matrix obtained by position-by-position correlation between the vector and the ultrasonic echo image feature vector,/a>
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix representing the calculation of a natural exponential function value raised to a power by a characteristic value at each position in the matrix,/v >
Affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor.
Compared with the prior art, the nondestructive testing method and system for the thickness of the steel fiber RPC cover plate are provided. Firstly, carrying out gram angle and field transformation on an obtained ultrasonic emission signal and an obtained ultrasonic echo signal to obtain an ultrasonic emission gram angle and field image and an ultrasonic echo gram angle and field image, then carrying out image blocking processing on the ultrasonic emission gram angle and field image and the ultrasonic echo gram angle and field image, obtaining an ultrasonic emission image characteristic vector and an ultrasonic echo image characteristic vector through a ViT model containing an embedded layer, and finally, carrying out decoder on a differential characteristic vector obtained by calculating the ultrasonic emission image characteristic vector and the ultrasonic echo image characteristic vector to obtain a decoding value for representing a thickness value. Thus, nondestructive detection of the thickness of the steel fiber RPC cover plate can be realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an application scenario diagram of a nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application.
Fig. 2 is a flow chart of a non-destructive testing method for steel fiber RPC cover plate thickness according to an embodiment of the present application.
Fig. 3 is a schematic diagram of the architecture of a nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application.
Fig. 4 is a flowchart of substep S130 of the nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application.
Fig. 5 is a flowchart of substep S140 of the nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application.
Fig. 6 is a block diagram of a non-destructive inspection system for steel fiber RPC cover plate thickness according to an embodiment of the present application.
Fig. 7 is a block diagram of the differential calculation module in a nondestructive testing system for steel fiber RPC cover thickness according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As described above, in the practical application of the steel fiber RPC cover plate, it is particularly important to detect the thickness of the steel fiber RPC cover plate. However, the existing steel fiber RPC cover plate thickness detection is mechanical thickness measurement, manual operation is needed, and scratches are caused on the surface of the steel fiber RPC cover plate. Thus, a more optimal non-destructive inspection scheme for steel fiber RPC cover plate thickness is desired.
Accordingly, considering that the current ultrasonic thickness measurement is widely applied to the measurement process of the thickness of the material, the ultrasonic thickness measurement device can avoid mechanical damage such as mechanical scratches caused by mechanical thickness measurement. The ultrasonic thickness measurement principle is as follows: when the ultrasonic pulse sent by the probe passes through the object to be measured and reaches the interface of the material, the pulse is reflected back to the probe, and the thickness of the material to be measured can be determined by measuring the propagation time of the ultrasonic wave in the material. Therefore, in the technical scheme of the application, the thickness measurement of the steel fiber RPC cover plate can be completed by utilizing the differential characteristic comparison between the ultrasonic emission signal and the ultrasonic echo signal. However, considering that the material of the steel fiber RPC cover plate is not uniformly distributed in actual preparation due to the large amount of information existing in the ultrasonic transmission signal and the ultrasonic echo signal, it is difficult to detect the thickness of the steel fiber RPC cover plate. Therefore, in this process, it is difficult to sufficiently extract the differential implicit characteristic distribution information of the ultrasonic emission signal and the ultrasonic echo signal, so that the thickness characteristics of the steel fiber RPC cover plate can be accurately expressed, and thus, the nondestructive thickness detection of the steel fiber RPC cover plate can be accurately performed.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
The development of deep learning and neural networks provides new solutions and schemes for mining the differential implicit characteristic distribution information of the ultrasonic emission signals and the ultrasonic echo signals.
Specifically, in the technical scheme of the present application, first, an ultrasonic transmission signal and an ultrasonic echo signal are acquired. It should be appreciated that, since the Gram angle field (Gramian angular field, GAF) is based on Gram principles, it can migrate a time series under a classical cartesian coordinate system to a polar coordinate system for representation, that is, the Gram angle field can convert time series data into image data, can preserve signal integrity information, and can well preserve the time dependence and correlation of the ultrasonic transmission signal and the ultrasonic echo signal, with similar timing characteristics as the original signal. In particular, the GAF may obtain a glamer angle sum field (Gramian angular sum field, GASF) and a glamer angle difference field (Gramian angular difference field, GADF) according to the trigonometric function used for encoding, and since the GADF is irreversible after conversion, in the technical solution of the present application, a GASF conversion mode capable of performing inverse conversion is selected to perform encoding of the ultrasonic transmission signal and the ultrasonic echo signal.
That is, specifically, the ultrasonic transmission signal and the ultrasonic echo signal are subjected to a gram angle and field transformation to obtain an ultrasonic transmission gram angle and field image and an ultrasonic echo gram angle and field image. In a specific example, the encoding steps of the ultrasonic transmission signal and the ultrasonic echo signal into the GASF image are as follows: for a time series of C dimensions = { Q1, Q2, …, QC }, where each dimension contains n sampling points Qi = { Qi1, qi2, …, qi }, the data of each dimension is first normalized. Then, all values in the data are integrated into [ -1,1], and after integration, the normalized numerical value is replaced by the value of the trigonometric function value Cos, and the Cartesian coordinates are replaced by the polar coordinates, so that the absolute time relation of the sequence is reserved.
Then, it is considered that the timing implicit feature distribution information on the propagation of the ultrasonic wave in the steel fiber RPC cover plate is a fine feature of a small scale in the image due to the ultrasonic wave transmission gram angle and the field image and the ultrasonic wave echo gram angle and the field image. In order to improve the expression capability of the ultrasonic wave emission gram angle and field image and the time sequence implicit characteristic of the ultrasonic wave echo gram angle and field image, which is transmitted in the steel fiber RPC cover plate, the accuracy of the thickness detection of the steel fiber RPC cover plate is improved. Therefore, in the technical solution of the present application, the ultrasound transmission gram angle and the field image and the ultrasound echo gram angle and the field image are processed in blocks to obtain a sequence of ultrasound transmission image blocks and a sequence of ultrasound echo image blocks. It should be appreciated that the dimensions of the individual image blocks in the sequence of ultrasound transmit image blocks and the sequence of ultrasound echo image blocks are reduced compared to the original image, and therefore the timing implication features of the ultrasound transmit and field images and the ultrasound echo and field images regarding the propagation of the ultrasound of small dimensions in the steel fibre RPC cover plate are no longer small-sized objects in the individual image blocks for detection with subsequent detection of steel fibre RPC cover plate thickness.
Then, the sequence of ultrasonic transmission image blocks and the sequence of ultrasonic echo image blocks are input to an embedding layer to obtain a sequence of ultrasonic transmission image block feature vectors and a sequence of ultrasonic echo image block feature vectors, and in particular, here, the embedding layer linearly projects each image block in the sequence of ultrasonic transmission image blocks and the ultrasonic echo image blocks as a one-dimensional embedding vector by a learning embedding matrix. The embedding process is realized by firstly arranging pixel values of all pixel positions of each image block in the sequence of the ultrasonic wave transmitting image blocks and the sequence of the ultrasonic wave echo image blocks into one-dimensional vectors, and then carrying out full-connection coding on the one-dimensional vectors by using a full-connection layer so as to realize embedding.
Further, it is considered that since each image block of the sequence of ultrasonic wave transmission image blocks and the sequence of ultrasonic wave echo image blocks is image data and there is a correlation between time-series implicit features concerning propagation of ultrasonic waves in a steel fiber RPC cover plate in each image block, feature mining is performed using a convolutional neural network model having excellent performance in implicit feature extraction of images. However, due to the inherent limitations of convolution operations, the pure CNN (Convolutional Neural Network) approach has difficulty learning explicit global and remote semantic information interactions. Therefore, in the technical scheme of the application, the sequence of the ultrasonic emission image block feature vector and the sequence of the ultrasonic echo image block feature vector are respectively encoded in a ViT model so as to respectively extract the context semantic association features of the time sequence implicit features of the ultrasonic wave propagating in the steel fiber RPC cover plate in each image block, thereby obtaining the ultrasonic emission image feature vector and the ultrasonic echo image feature vector. It should be appreciated that ViT may process the individual image blocks to be detected directly by a self-attention mechanism like a transducer, thereby extracting contextual semantic-related feature information about timing implicit features of the propagation of the ultrasound waves in the steel fiber RPC cover plate in the individual ultrasound transmit image blocks of the sequence of ultrasound transmit image blocks and the individual ultrasound echo image blocks of the sequence of ultrasound echo image blocks, respectively.
And then, further calculating a differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector so as to represent differential feature distribution information of time sequence related features of ultrasonic wave propagation in the steel fiber RPC cover plate in the ultrasonic emission signal and the ultrasonic echo signal, namely propagation time differential feature information of the ultrasonic emission signal and the ultrasonic echo signal in the steel fiber RPC cover plate.
Then, the differential feature vector is subjected to decoding regression in a decoder as a decoded feature vector to obtain a decoded value representing the thickness value. That is, the difference characteristic information of the propagation time sequence of the ultrasonic wave transmitting signal and the ultrasonic wave echo signal in the steel fiber RPC cover plate is used for decoding to obtain the difference change of the propagation time difference of the ultrasonic wave transmitting signal and the ultrasonic wave echo signal in the steel fiber RPC cover plate, so that the thickness detection of the steel fiber RPC cover plate is performed.
In particular, in the technical solution of the present application, here, when calculating the differential feature vector between the ultrasound emission image feature vector and the ultrasound echo image feature vector, if the position-by-position correlation between the ultrasound emission image feature vector and the ultrasound echo image feature vector, that is, the feature value granularity correlation thereof, and the correlation of the ultrasound emission image feature vector and the ultrasound echo image feature vector as a whole with respect to the regression probability density distribution, that is, the vector granularity correlation thereof, can be improved, the expression effect of the differential feature vector between the ultrasound emission image feature vector and the ultrasound echo image feature vector can be improved, thereby improving the accuracy of the decoding result of the differential feature vector by the decoder.
Accordingly, the applicant of the present application separately calculates the ultrasound emission image feature vectors, e.g., denoted as
And said ultrasound echo image feature vector, e.g. denoted +.>
Affine mapping factors of the association-probability density distribution expressed as:
That is, by constructing the ultrasonic emission image characteristic directionMeasuring amount
And the ultrasound echo image feature vector +.>
The correlation feature space between them and the regression probability density distribution space represented by Gaussian probability density can be obtained by dispersing the ultrasonic wave into the image feature vector +.>
And the ultrasound echo image feature vector +.>
Mapping into affine homography subspaces within an associated feature space and a regression probability density distribution space, respectively, to extract affine homography-compliant representations of feature representations within the associated feature domain and the regression probability density distribution space by mapping factor values with the associated-probability density distribution affine >
and />
The ultrasonic emission image feature vector is respectively +.>
And the ultrasound echo image feature vector +.>
Weighting is performed to promote the feature vector of the ultrasonic emission image>
And the ultrasound echo image feature vector +.>
The correlation with respect to its eigenvalue granularity represents the consistency of vector granularity across the probability density distribution. Thus, the ultrasonic emission image characteristics are improvedSyndrome vector->
And the ultrasound echo image feature vector +.>
The expression effect of the differential feature vector between the two, thereby improving the accuracy of the decoding result of the differential feature vector through a decoder. Like this, can accurately carry out the thickness detection of steel fiber RPC apron to when improving thickness detection accuracy, avoid causing the mechanical damage of steel fiber RPC apron.
Fig. 1 is an application scenario diagram of a nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, an ultrasonic transmission signal (e.g., 901 illustrated in fig. 1) and an ultrasonic echo signal (e.g., 902 illustrated in fig. 1) are acquired, wherein 903 illustrated in fig. 1 is a steel fiber RPC cover plate, 904 is an ultrasonic device adapted to transmit an ultrasonic transmission signal and receive an ultrasonic echo signal, and then the ultrasonic transmission signal and the ultrasonic echo signal are input to a server (e.g., 905 illustrated in fig. 1) where a nondestructive detection algorithm for steel fiber RPC cover plate thickness is deployed, wherein the server is capable of processing the ultrasonic transmission signal and the ultrasonic echo signal using the nondestructive detection algorithm for steel fiber RPC cover plate thickness to obtain a decoded value for representing a thickness value.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Fig. 2 is a flow chart of a non-destructive testing method for steel fiber RPC cover plate thickness according to an embodiment of the present application. As shown in fig. 2, a nondestructive testing method for the thickness of a steel fiber RPC cover plate according to an embodiment of the present application includes the steps of: s110, acquiring an ultrasonic emission signal and an ultrasonic echo signal; s120, carrying out gram angle and field transformation on the ultrasonic wave emission signal and the ultrasonic wave echo signal to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image; s130, performing image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image, and then obtaining an ultrasonic wave emission image characteristic vector and an ultrasonic wave echo image characteristic vector through a ViT model containing an embedded layer; s140, calculating a differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector; and S150, passing the differential feature vector through a decoder to obtain a decoded value, wherein the decoded value is used for representing the thickness value.
Fig. 3 is a schematic diagram of the architecture of a nondestructive testing method for steel fiber RPC cover thickness according to an embodiment of the present application. As shown in fig. 3, in the network architecture, first, an ultrasonic transmission signal and an ultrasonic echo signal are acquired; then, carrying out gram angle and field transformation on the ultrasonic wave emission signal and the ultrasonic wave echo signal to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image; then, the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image are subjected to image blocking processing, and an ultrasonic wave emission image characteristic vector and an ultrasonic wave echo image characteristic vector are obtained through a ViT model containing an embedded layer; then, calculating a differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector; finally, the differential feature vector is passed through a decoder to obtain decoded values, which are used to represent thickness values.
More specifically, in step S110, an ultrasonic transmission signal and an ultrasonic echo signal are acquired. The existing steel fiber RPC cover plate thickness detection is mechanical thickness measurement, manual operation is needed, and scratches can be caused on the surface of the steel fiber RPC cover plate. Considering that the current ultrasonic thickness measurement is widely applied in the process of measuring the thickness of a material, the ultrasonic thickness measurement device can avoid mechanical damages such as mechanical scratches caused by mechanical thickness measurement. Therefore, in the technical scheme of the application, the thickness measurement of the steel fiber RPC cover plate can be completed by utilizing the differential characteristic comparison between the ultrasonic emission signal and the ultrasonic echo signal. However, since there is a large amount of information in the ultrasonic transmission signal and the ultrasonic echo signal, the material of the steel fiber RPC cover plate is not uniformly distributed in actual preparation, which makes it difficult to detect the thickness of the steel fiber RPC cover plate. Therefore, in the application, the thickness characteristics of the steel fiber RPC cover plate can be accurately expressed by mining the differential implicit characteristic distribution information of the ultrasonic emission signal and the ultrasonic echo signal, so that the nondestructive thickness detection of the steel fiber RPC cover plate can be accurately carried out.
More specifically, in step S120, the ultrasonic transmission signal and the ultrasonic echo signal are subjected to a gram angle and field transformation to obtain an ultrasonic transmission gram angle and field image and an ultrasonic echo gram angle and field image.
It should be appreciated that, since the Gram angle field (Gramian angular field, GAF) is based on Gram principles, it can migrate a time series under a classical cartesian coordinate system to a polar coordinate system for representation, that is, the Gram angle field can convert time series data into image data, can preserve signal integrity information, and can well preserve the time dependence and correlation of the ultrasonic transmission signal and the ultrasonic echo signal, with similar timing characteristics as the original signal. In particular, the GAF may obtain a glamer angle sum field (Gramian angular sum field, GASF) and a glamer angle difference field (Gramian angular difference field, GADF) according to the trigonometric function used for encoding, and since the GADF is irreversible after conversion, in the technical solution of the present application, a GASF conversion mode capable of performing inverse conversion is selected to perform encoding of the ultrasonic transmission signal and the ultrasonic echo signal.
That is, specifically, the ultrasonic transmission signal and the ultrasonic echo signal are subjected to a gram angle and field transformation to obtain an ultrasonic transmission gram angle and field image and an ultrasonic echo gram angle and field image. In a specific example, the encoding steps of the ultrasonic transmission signal and the ultrasonic echo signal into the GASF image are as follows: for a time series of C dimensions = { Q1, Q2, …, QC }, where each dimension contains n sampling points Qi = { Qi1, qi2, …, qi }, the data of each dimension is first normalized. Then, all values in the data are integrated into [ -1,1], and after integration, the normalized numerical value is replaced by the value of the trigonometric function value Cos, and the Cartesian coordinates are replaced by the polar coordinates, so that the absolute time relation of the sequence is reserved.
More specifically, in step S130, the ultrasound transmission gram angle and field image and the ultrasound echo gram angle and field image are subjected to image blocking processing and then passed through a ViT model including an embedded layer to obtain an ultrasound transmission image feature vector and an ultrasound echo image feature vector. And the ultrasonic wave emission gram angle and field image and the time sequence implicit characteristic distribution information about the ultrasonic wave propagation in the steel fiber RPC cover plate in the ultrasonic wave echo gram angle and field image are small-scale fine characteristics in the image. In order to improve the expression capability of the ultrasonic wave emission gram angle and field image and the time sequence implicit characteristic of the ultrasonic wave echo gram angle and field image, which is transmitted in the steel fiber RPC cover plate, the accuracy of the thickness detection of the steel fiber RPC cover plate is improved. Thus, the ultrasound transmit and echo gram and field images are segmented to obtain a sequence of ultrasound transmit and echo image blocks. It should be appreciated that the dimensions of the individual image blocks in the sequence of ultrasound transmit image blocks and the sequence of ultrasound echo image blocks are reduced compared to the original image, and therefore the timing implication features of the ultrasound transmit and field images and the ultrasound echo and field images regarding the propagation of the ultrasound of small dimensions in the steel fibre RPC cover plate are no longer small-sized objects in the individual image blocks for detection with subsequent detection of steel fibre RPC cover plate thickness.
Accordingly, in one specific example, as shown in fig. 4, after performing image blocking processing on the ultrasonic emission gram angle and the field image and the ultrasonic echo gram angle and the field image, obtaining an ultrasonic emission image feature vector and an ultrasonic echo image feature vector through a ViT model including an embedded layer, including: s131, performing image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image respectively to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks; s132, respectively inputting the sequence of the ultrasonic wave emission image blocks and the sequence of the ultrasonic wave echo image blocks into the embedded layer to obtain a sequence of ultrasonic wave emission image block feature vectors and a sequence of ultrasonic wave echo image block feature vectors; and S133, passing the sequence of the ultrasonic wave emission image block characteristic vector and the sequence of the ultrasonic wave echo image block characteristic vector through the ViT model to obtain the ultrasonic wave emission image characteristic vector and the ultrasonic wave echo image characteristic vector.
It should be understood that the embedding is implemented by first arranging the pixel values of all pixel positions of each image block in the sequence of ultrasonic transmission image blocks and the sequence of ultrasonic echo image blocks into a one-dimensional vector, and then performing full-connection encoding on the one-dimensional vector by using a full-connection layer.
It should be understood that each image block of the sequence of ultrasonic wave transmission image blocks and the sequence of ultrasonic wave echo image blocks is image data, and that there is a correlation between time-series implicit features concerning propagation of ultrasonic waves in a steel fiber RPC cover plate in each image block, and therefore, feature mining is performed using a convolutional neural network model having excellent performance in implicit feature extraction of images. However, due to the inherent limitations of convolution operations, pure CNN methods have difficulty learning explicit global and remote semantic information interactions. Therefore, in the technical scheme of the application, the sequence of the ultrasonic emission image block feature vector and the sequence of the ultrasonic echo image block feature vector are respectively encoded in a ViT model so as to respectively extract the context semantic association features of the time sequence implicit features of the ultrasonic wave propagating in the steel fiber RPC cover plate in each image block, thereby obtaining the ultrasonic emission image feature vector and the ultrasonic echo image feature vector. It should be appreciated that ViT may process the individual image blocks to be detected directly by a self-attention mechanism like a transducer, thereby extracting contextual semantic-related feature information about timing implicit features of the propagation of the ultrasound waves in the steel fiber RPC cover plate in the individual ultrasound transmit image blocks of the sequence of ultrasound transmit image blocks and the individual ultrasound echo image blocks of the sequence of ultrasound echo image blocks, respectively.
The convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition and the like. The convolutional neural network may include an input layer, a hidden layer, and an output layer, where the hidden layer may include a convolutional layer, a pooling layer, an activation layer, a full connection layer, etc., where the previous layer performs a corresponding operation according to input data, outputs an operation result to the next layer, and obtains a final result after the input initial data is subjected to a multi-layer operation.
More specifically, in step S140, a differential feature vector between the ultrasound transmission image feature vector and the ultrasound echo image feature vector is calculated. The differential characteristic distribution information of the ultrasonic wave emission signal and the ultrasonic wave echo signal, namely the differential characteristic information of the propagation time of the ultrasonic wave emission signal and the ultrasonic wave echo signal in the steel fiber RPC cover plate, about the time sequence related characteristic of the ultrasonic wave propagation in the steel fiber RPC cover plate is expressed.
Accordingly, in one specific example, as shown in fig. 5, calculating a differential feature vector between the ultrasound transmission image feature vector and the ultrasound echo image feature vector includes: s141, calculating a correlation-probability density distribution affine mapping factor between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor; s142, weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector by taking the affine mapping factors of the first association-probability density distribution and the affine mapping factors of the second association-probability density distribution as weights so as to obtain an optimized ultrasonic emission image feature vector and an optimized ultrasonic echo image feature vector; and S143, calculating a difference according to positions between the optimized ultrasonic wave emission image characteristic vector and the optimized ultrasonic wave echo image characteristic vector to obtain the difference characteristic vector.
In particular, in the technical solution of the present application, here, when calculating the differential feature vector between the ultrasound emission image feature vector and the ultrasound echo image feature vector, if the position-by-position correlation between the ultrasound emission image feature vector and the ultrasound echo image feature vector, that is, the feature value granularity correlation thereof, and the correlation of the ultrasound emission image feature vector and the ultrasound echo image feature vector as a whole with respect to the regression probability density distribution, that is, the vector granularity correlation thereof, can be improved, the expression effect of the differential feature vector between the ultrasound emission image feature vector and the ultrasound echo image feature vector can be improved, thereby improving the accuracy of the decoding result of the differential feature vector by the decoder. Accordingly, the applicant of the present application calculates the correlation-probability density distribution affine mapping factor of the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector, respectively.
Accordingly, in one specific example, calculating a correlation-probability density distribution affine mapping factor between the ultrasound transmit image feature vector and the ultrasound echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor comprises: calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor; wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector, +.>
A correlation matrix obtained for a position-by-position correlation between the ultrasound transmit image feature vector and the ultrasound echo image feature vector,>
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix representing the calculation of a natural exponential function value raised to a power by a characteristic value at each position in the matrix,/v>
Affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor.
That is, by constructionAn associated feature space between the ultrasound transmit image feature vector and the ultrasound echo image feature vector and a regression probability density distribution space represented by Gaussian probability density, wherein the feature representation is extracted by mapping the ultrasound transmit image feature vector and the ultrasound echo image feature vector into affine homography subspaces within the associated feature space and the regression probability density distribution space, respectively, to extract affine homography-compliant representations of feature representations within the associated feature domain and the regression probability density distribution, and affine mapping factor values by distributing affine mapping factor values with the associated-probability density 
and />
Weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector respectively can promote the consistency of vector granularity on probability density distribution of the association expression of the ultrasonic emission image feature vector and the ultrasonic echo image feature vector relative to the granularity of the feature value. Therefore, the expression effect of the differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector is improved, and the accuracy of the decoding result of the differential feature vector through the decoder is improved. Like this, can accurately carry out the thickness detection of steel fiber RPC apron to when improving thickness detection accuracy, avoid causing the mechanical damage of steel fiber RPC apron.
Accordingly, in one specific example, calculating the per-position difference between the optimized ultrasound transmit image feature vector and the optimized ultrasound echo image feature vector to obtain the differential feature vector includes: calculating the differential feature vector between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector by using the following differential formula; wherein, the difference formula is:
wherein ,
representing the optimized ultrasound emission image feature vector, and (2)>
Representing the optimized ultrasound echo image feature vector, < >>
Representing the differential eigenvector,>
representing the difference by location.
More specifically, in step S150, the differential feature vector is passed through a decoder to obtain a decoded value, which is used to represent a thickness value. That is, the difference characteristic information of the propagation time sequence of the ultrasonic wave transmitting signal and the ultrasonic wave echo signal in the steel fiber RPC cover plate is used for decoding to obtain the difference change of the propagation time difference of the ultrasonic wave transmitting signal and the ultrasonic wave echo signal in the steel fiber RPC cover plate, so that the thickness detection of the steel fiber RPC cover plate is performed.
Accordingly, in one specific example, passing the differential feature vector through a decoder to obtain a decoded value, the decoded value being used to represent a thickness value, comprising: performing decoding regression on the differential feature vector with a decoding formula using a plurality of fully connected layers of the decoder to obtain the decoded value, wherein the decoding formula is:
, wherein 
Is the differential eigenvector,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
In summary, according to the nondestructive testing method for the thickness of the steel fiber RPC cover plate according to the embodiment of the application, firstly, the acquired ultrasonic emission signals and ultrasonic echo signals are subjected to the gram angle and field transformation to obtain ultrasonic emission gram angles and field images and ultrasonic echo gram angles and field images, then, the ultrasonic emission gram angles and field images and the ultrasonic echo gram angles and field images are subjected to the image blocking processing and then pass through a ViT model containing an embedded layer to obtain ultrasonic emission image feature vectors and ultrasonic echo image feature vectors, and finally, differential feature vectors obtained by calculating the ultrasonic emission image feature vectors and the ultrasonic echo image feature vectors are passed through a decoder to obtain decoding values for representing thickness values. Thus, nondestructive detection of the thickness of the steel fiber RPC cover plate can be realized.
Fig. 6 is a block diagram of a non-destructive inspection system 100 for steel fiber RPC cover plate thickness according to an embodiment of the present application. As shown in fig. 6, a nondestructive inspection system 100 for steel fiber RPC cover thickness according to an embodiment of the present application includes: the signal acquisition module 110 is used for acquiring an ultrasonic emission signal and an ultrasonic echo signal; a gram angle and field conversion module 120, configured to perform gram angle and field conversion on the ultrasonic transmission signal and the ultrasonic echo signal to obtain an ultrasonic transmission gram angle and field image and an ultrasonic echo gram angle and field image; the encoding module 130 is configured to perform image blocking processing on the ultrasonic emission gram angle and the field image and the ultrasonic echo gram angle and the field image, and obtain an ultrasonic emission image feature vector and an ultrasonic echo image feature vector through a ViT model including an embedded layer; a difference calculation module 140 for calculating a difference feature vector between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector; and a decoding module 150, configured to pass the differential feature vector through a decoder to obtain a decoded value, where the decoded value is used to represent a thickness value.
In one example, in the nondestructive testing system 100 for steel fiber RPC cover thickness described above, the encoding module 130 is configured to: respectively carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks; respectively inputting the sequence of the ultrasonic emission image blocks and the sequence of the ultrasonic echo image blocks into the embedded layer to obtain a sequence of ultrasonic emission image block feature vectors and a sequence of ultrasonic echo image block feature vectors; and passing the sequence of ultrasonic emission image block feature vectors and the sequence of ultrasonic echo image block feature vectors through the ViT model to obtain the ultrasonic emission image feature vectors and the ultrasonic echo image feature vectors, respectively.
In one example, in the nondestructive testing system 100 for steel fiber RPC cover thickness described above, as shown in fig. 7, the differential calculating module 140 includes: a correlation-probability density distribution affine mapping factor calculating unit 141 for calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor; a weighting optimization unit 142, configured to weight the ultrasound emission image feature vector and the ultrasound echo image feature vector with the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor as weights to obtain an optimized ultrasound emission image feature vector and an optimized ultrasound echo image feature vector; and a per-position difference unit 143 for calculating a per-position difference between the optimized ultrasonic transmission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector.
In one example, in the nondestructive testing system 100 for steel fiber RPC cover thickness described above, the correlation-probability density distribution affine mapping factor calculating unit 141 is configured to: calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor; wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector, +.>
A correlation matrix obtained for a position-by-position correlation between the ultrasound transmit image feature vector and the ultrasound echo image feature vector,>
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix representing the computation in terms of individual positions in the matrixNatural exponential function value with characteristic value of power, +. >
Affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor.
In one example, in the nondestructive inspection system 100 for steel fiber RPC cover thickness described above, the differential by position unit 143 is configured to: calculating the differential feature vector between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector by using the following differential formula; wherein, the difference formula is:
wherein ,
representing the optimized ultrasound emission image feature vector, and (2)>
Representing the optimized ultrasound echo image feature vector, < >>
Representing the differential eigenvector,>
representing the difference by location.
In one example, in the nondestructive inspection system 100 for steel fiber RPC cover thickness described above, the decoding module 150 is configured to: performing decoding regression on the differential feature vector with a decoding formula using a plurality of fully connected layers of the decoder to obtain the decoded value, wherein the decoding formula is:
, wherein />
Is the differential eigenvector,>
is the decoded value,/->
Is a weight matrix, < > >
Representing a matrix multiplication.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described nondestructive inspection system 100 for steel fiber RPC cover thickness have been described in detail in the above description of the nondestructive inspection method for steel fiber RPC cover thickness with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
As described above, the nondestructive testing system 100 for steel fiber RPC cover thickness according to the embodiment of the present application may be implemented in various wireless terminals, such as a server or the like having a nondestructive testing algorithm for steel fiber RPC cover thickness. In one example, the non-destructive inspection system 100 for steel fiber RPC cover thickness according to embodiments of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the nondestructive testing system 100 for steel fiber RPC cover thickness may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the nondestructive testing system 100 for steel fiber RPC cover thickness can equally be one of many hardware modules of the wireless terminal.
Alternatively, in another example, the nondestructive testing system 100 for steel fiber RPC cover thickness and the wireless terminal may be separate devices, and the nondestructive testing system 100 for steel fiber RPC cover thickness may be connected to the wireless terminal through a wired and/or wireless network, and transmit the interactive information in a agreed data format.
According to another aspect of the present application, there is also provided a non-volatile computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a computer, can perform a method as described above.
Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.
All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.
This application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (10)
1. A method for non-destructive testing of steel fiber RPC cover thickness comprising:
acquiring an ultrasonic emission signal and an ultrasonic echo signal;
carrying out gram angle and field transformation on the ultrasonic wave emission signal and the ultrasonic wave echo signal to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image;
performing image blocking processing on the ultrasonic emission gram angle and the field image and the ultrasonic echo gram angle and the field image, and then obtaining an ultrasonic emission image feature vector and an ultrasonic echo image feature vector through a ViT model containing an embedded layer;
calculating a differential feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector; and
the differential feature vector is passed through a decoder to obtain decoded values, which are used to represent thickness values.
2. The nondestructive testing method for steel fiber RPC cover thickness according to claim 1, wherein the ultrasonic emission and field images and the ultrasonic echo and field images are subjected to image blocking processing and then passed through a ViT model containing an embedded layer to obtain ultrasonic emission and echo image feature vectors, comprising:
Respectively carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks;
respectively inputting the sequence of the ultrasonic emission image blocks and the sequence of the ultrasonic echo image blocks into the embedded layer to obtain a sequence of ultrasonic emission image block feature vectors and a sequence of ultrasonic echo image block feature vectors; and
and respectively passing the sequence of the ultrasonic emission image block characteristic vectors and the sequence of the ultrasonic echo image block characteristic vectors through the ViT model to obtain the ultrasonic emission image characteristic vectors and the ultrasonic echo image characteristic vectors.
3. The nondestructive testing method for steel fiber RPC cover thickness of claim 2, wherein calculating a differential eigenvector between the ultrasonic emission image eigenvector and the ultrasonic echo image eigenvector comprises:
calculating a correlation-probability density distribution affine mapping factor between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor;
Weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector by taking the affine mapping factor of the first association-probability density distribution and the affine mapping factor of the second association-probability density distribution as weights so as to obtain an optimized ultrasonic emission image feature vector and an optimized ultrasonic echo image feature vector; and
and calculating the difference according to positions between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector.
4. A non-destructive inspection method for steel fiber RPC cover plate thickness according to claim 3, wherein calculating a correlation-probability density distribution affine mapping factor between the ultrasound transmit image feature vector and the ultrasound echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor comprises:
calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor;
Wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector,
a correlation matrix obtained for a position-by-position correlation between the ultrasound transmit image feature vector and the ultrasound echo image feature vector,>
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix, the exponential operation representing a calculation toThe eigenvalues of each position in the matrix are natural exponential function values of powers,
affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor.
5. The method for non-destructive testing of steel fiber RPC cover thickness according to claim 4, wherein calculating a difference by location between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the differential feature vector comprises:
calculating the differential feature vector between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector by using the following differential formula;
Wherein, the difference formula is:
wherein ,
representing the optimized ultrasound emission image feature vector, and (2)>
Representing the optimized ultrasound echo image feature vector, < >>
Representing the differential eigenvector,>
representing the difference by location.
6. The method for non-destructive inspection of steel fiber RPC cap plate thickness according to claim 5, wherein passing the differential eigenvector through a decoder to obtain a decoded value, the decoded value being used to represent a thickness value, comprises:
performing decoding regression on the differential feature vector with a decoding formula using a plurality of fully connected layers of the decoder to obtain the decoded value, wherein the decoding formula is:
, wherein />
Is the differential eigenvector,>
is the decoded value,/->
Is a weight matrix, < >>
Representing a matrix multiplication.
7. A non-destructive inspection system for steel fiber RPC cover thickness, comprising:
the signal acquisition module is used for acquiring an ultrasonic emission signal and an ultrasonic echo signal;
the gram angle and field conversion module is used for carrying out gram angle and field conversion on the ultrasonic wave emission signal and the ultrasonic wave echo signal so as to obtain an ultrasonic wave emission gram angle and field image and an ultrasonic wave echo gram angle and field image;
The encoding module is used for carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image, and obtaining ultrasonic wave emission image feature vectors and ultrasonic wave echo image feature vectors through a ViT model containing an embedded layer;
the difference calculation module is used for calculating a difference feature vector between the ultrasonic emission image feature vector and the ultrasonic echo image feature vector; and a decoding module for passing the differential feature vector through a decoder to obtain a decoded value, the decoded value being indicative of a thickness value.
8. The non-destructive inspection system for steel fiber RPC cover thicknesses of claim 7, wherein the encoding module is configured to:
respectively carrying out image blocking processing on the ultrasonic wave emission gram angle and the field image and the ultrasonic wave echo gram angle and the field image to obtain a sequence of ultrasonic wave emission image blocks and a sequence of ultrasonic wave echo image blocks;
respectively inputting the sequence of the ultrasonic emission image blocks and the sequence of the ultrasonic echo image blocks into the embedded layer to obtain a sequence of ultrasonic emission image block feature vectors and a sequence of ultrasonic echo image block feature vectors; and passing the sequence of ultrasonic emission image block feature vectors and the sequence of ultrasonic echo image block feature vectors through the ViT model to obtain the ultrasonic emission image feature vectors and the ultrasonic echo image feature vectors, respectively.
9. The non-destructive inspection system for steel fiber RPC cover thicknesses of claim 8, wherein the differential calculation module comprises:
a correlation-probability density distribution affine mapping factor calculating unit for calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector to obtain a first correlation-probability density distribution affine mapping factor and a second correlation-probability density distribution affine mapping factor;
the weighting optimization unit is used for weighting the ultrasonic emission image feature vector and the ultrasonic echo image feature vector by taking the affine mapping factors of the first association-probability density distribution and the affine mapping factors of the second association-probability density distribution as weights so as to obtain an optimized ultrasonic emission image feature vector and an optimized ultrasonic echo image feature vector; and a per-position difference unit for calculating a per-position difference between the optimized ultrasonic emission image feature vector and the optimized ultrasonic echo image feature vector to obtain the difference feature vector.
10. The nondestructive inspection system for steel fiber RPC cover thickness of claim 9 wherein the correlation-probability density distribution affine mapping factor calculation unit is configured to:
Calculating a correlation-probability density distribution affine mapping factor between the ultrasonic transmission image feature vector and the ultrasonic echo image feature vector in the following optimization formula to obtain the first correlation-probability density distribution affine mapping factor and the second correlation-probability density distribution affine mapping factor;
wherein, the optimization formula is:
wherein ,
representing the ultrasound emission image feature vector, +.>
Representing the ultrasound echo image feature vector,
a correlation obtained for a position-by-position correlation between the ultrasound transmit image feature vector and the ultrasound echo image feature vectorUnion matrix->
and />
Is the mean vector and the position-by-position variance matrix of a Gaussian density map formed by the ultrasonic emission image feature vector and the ultrasonic echo image feature vector,>
representing matrix multiplication +.>
An exponential operation representing a matrix representing a calculation of a natural exponential function value exponentiated by eigenvalues of respective positions in the matrix,
affine mapping factors representing said first correlation-probability density distribution,>
representing the second associative-probability density distribution affine mapping factor. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310421390.9A CN116147548B (en) | 2023-04-19 | 2023-04-19 | Nondestructive testing method and system for thickness of steel fiber RPC cover plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310421390.9A CN116147548B (en) | 2023-04-19 | 2023-04-19 | Nondestructive testing method and system for thickness of steel fiber RPC cover plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116147548A true CN116147548A (en) | 2023-05-23 |
| CN116147548B CN116147548B (en) | 2023-07-25 |
Family
ID=86350993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310421390.9A Active CN116147548B (en) | 2023-04-19 | 2023-04-19 | Nondestructive testing method and system for thickness of steel fiber RPC cover plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116147548B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117686588A (en) * | 2024-02-04 | 2024-03-12 | 新疆盛诚工程建设有限责任公司 | Nondestructive monitoring system and method for welding quality of gas pipeline |
| CN117849193A (en) * | 2024-03-07 | 2024-04-09 | 江西荧光磁业有限公司 | Online crack damage monitoring method for neodymium iron boron sintering |
| CN117686588B (en) * | 2024-02-04 | 2024-05-10 | 新疆盛诚工程建设有限责任公司 | Nondestructive monitoring system and method for welding quality of gas pipeline |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090216535A1 (en) * | 2008-02-22 | 2009-08-27 | Avraham Entlis | Engine For Speech Recognition |
| CN102183582A (en) * | 2011-01-27 | 2011-09-14 | 中国商用飞机有限责任公司 | Ultrasonic nondestructive testing device and method |
| CN102435675A (en) * | 2011-09-23 | 2012-05-02 | 南昌航空大学 | Ultrasonic TOFD technology detection method for butt seam of different thickness plates |
| CN105030279A (en) * | 2015-06-24 | 2015-11-11 | 华南理工大学 | Ultrasonic RF (radio frequency) time sequence-based tissue characterization method |
| CN110967404A (en) * | 2019-11-25 | 2020-04-07 | 苏州热工研究院有限公司 | Nuclear power station conventional island shaft class forge piece phased array ultrasonic detection system and detection method |
| US20210239450A1 (en) * | 2020-01-31 | 2021-08-05 | The Trustees Of Columbia University In The City Of New York | System, method, computer-accessible medium, and apparatus facilitating ultra-high resolution optical coherence tomography for automated detection of diseases |
| CN113566692A (en) * | 2021-07-23 | 2021-10-29 | 国网天津市电力公司电力科学研究院 | Nondestructive testing method for quality of cable cement protection cover plate |
| CN113947583A (en) * | 2021-10-20 | 2022-01-18 | 辽宁师范大学 | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image |
| CN114972751A (en) * | 2022-05-11 | 2022-08-30 | 平安科技（深圳）有限公司 | Medical image recognition method, electronic device and storage medium |
| CN218270638U (en) * | 2022-10-13 | 2023-01-10 | 河北省弘瑞石油化工锅炉压力容器检测站 | Ultrasonic thickness gauge with probe protection function |
| CN115791969A (en) * | 2022-12-08 | 2023-03-14 | 深圳量云能源网络科技有限公司 | Jacket underwater crack detection system and method based on acoustic emission signals |
-
2023
- 2023-04-19 CN CN202310421390.9A patent/CN116147548B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090216535A1 (en) * | 2008-02-22 | 2009-08-27 | Avraham Entlis | Engine For Speech Recognition |
| CN102183582A (en) * | 2011-01-27 | 2011-09-14 | 中国商用飞机有限责任公司 | Ultrasonic nondestructive testing device and method |
| CN102435675A (en) * | 2011-09-23 | 2012-05-02 | 南昌航空大学 | Ultrasonic TOFD technology detection method for butt seam of different thickness plates |
| CN105030279A (en) * | 2015-06-24 | 2015-11-11 | 华南理工大学 | Ultrasonic RF (radio frequency) time sequence-based tissue characterization method |
| CN110967404A (en) * | 2019-11-25 | 2020-04-07 | 苏州热工研究院有限公司 | Nuclear power station conventional island shaft class forge piece phased array ultrasonic detection system and detection method |
| US20210239450A1 (en) * | 2020-01-31 | 2021-08-05 | The Trustees Of Columbia University In The City Of New York | System, method, computer-accessible medium, and apparatus facilitating ultra-high resolution optical coherence tomography for automated detection of diseases |
| CN113566692A (en) * | 2021-07-23 | 2021-10-29 | 国网天津市电力公司电力科学研究院 | Nondestructive testing method for quality of cable cement protection cover plate |
| CN113947583A (en) * | 2021-10-20 | 2022-01-18 | 辽宁师范大学 | Weld joint nondestructive testing method based on deep learning two-dimensional time sequence image |
| CN114972751A (en) * | 2022-05-11 | 2022-08-30 | 平安科技（深圳）有限公司 | Medical image recognition method, electronic device and storage medium |
| CN218270638U (en) * | 2022-10-13 | 2023-01-10 | 河北省弘瑞石油化工锅炉压力容器检测站 | Ultrasonic thickness gauge with probe protection function |
| CN115791969A (en) * | 2022-12-08 | 2023-03-14 | 深圳量云能源网络科技有限公司 | Jacket underwater crack detection system and method based on acoustic emission signals |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117686588A (en) * | 2024-02-04 | 2024-03-12 | 新疆盛诚工程建设有限责任公司 | Nondestructive monitoring system and method for welding quality of gas pipeline |
| CN117686588B (en) * | 2024-02-04 | 2024-05-10 | 新疆盛诚工程建设有限责任公司 | Nondestructive monitoring system and method for welding quality of gas pipeline |
| CN117849193A (en) * | 2024-03-07 | 2024-04-09 | 江西荧光磁业有限公司 | Online crack damage monitoring method for neodymium iron boron sintering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116147548B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104166804B (en) | A kind of operation mode discrimination method based on time-frequency domain list source point sparse component analysis | |
| CN108564606B (en) | Heterogeneous image block matching method based on image conversion | |
| CN116147548B (en) | Nondestructive testing method and system for thickness of steel fiber RPC cover plate | |
| Li et al. | Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing | |
| Huang et al. | A provably convergent scheme for compressive sensing under random generative priors | |
| Khoshnoudian et al. | Structural damage detection using FRF data, 2D-PCA, artificial neural networks and imperialist competitive algorithm simultaneously | |
| Das et al. | A data-driven physics-informed method for prognosis of infrastructure systems: Theory and application to crack prediction | |
| CN116563302B (en) | Intelligent medical information management system and method thereof | |
| Olivieri et al. | Near-field acoustic holography analysis with convolutional neural networks | |
| Zhang et al. | Timber damage identification using dynamic broad network and ultrasonic signals | |
| CN111445515A (en) | Underground cylinder target radius estimation method and system based on feature fusion network | |
| Ahmadvand et al. | 1D-CNNs for autonomous defect detection in bridge decks using ground penetrating radar | |
| CN116665114B (en) | Multi-mode-based remote sensing scene identification method, system and medium | |
| Liu et al. | Deep learning in frequency domain for inverse identification of nonhomogeneous material properties | |
| Liao et al. | An innovative deep neural network coordinating with percussion-based technique for automatic detection of concrete cavity defects | |
| Zhang et al. | Reconstruction of porous media using an information variational auto-encoder | |
| CN116182089A (en) | Long-distance conveying pipeline leakage detection method and system | |
| CN116310812A (en) | High-resolution remote sensing image semantic change detection method based on semi-supervised semantic segmentation contrast learning | |
| CN112085779B (en) | Wave parameter estimation method and device | |
| CN112818762B (en) | Large-size composite material and rapid nondestructive testing method for sandwich structure thereof | |
| Yun et al. | A multidimensional data fusion neural network for damage localization using ultrasonic guided wave | |
| CN112528869B (en) | Phase-free data imaging method based on complex neural network | |
| Dizaji et al. | Machine-learning to see defects: a hybrid attention-ConvLSTM-based convolutional neural network deep learning architecture for structural damage detection | |
| Zhang et al. | Nondestructive detection of fiber content in steel fiber reinforced concrete through percussion method coordinated with a hybrid deep learning network | |
| Zhang et al. | Hybrid Probabilistic Deep Learning for Damage Identification |
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 |