CN114689598A - Terahertz wave-based internal defect imaging method, electronic device, and storage medium - Google Patents
Terahertz wave-based internal defect imaging method, electronic device, and storage medium Download PDFInfo
- Publication number
- CN114689598A CN114689598A CN202210302242.0A CN202210302242A CN114689598A CN 114689598 A CN114689598 A CN 114689598A CN 202210302242 A CN202210302242 A CN 202210302242A CN 114689598 A CN114689598 A CN 114689598A
- Authority
- CN
- China
- Prior art keywords
- defect
- terahertz
- detection
- wave
- waveform
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 202
- 238000003384 imaging method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 127
- 238000012549 training Methods 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 32
- 238000001228 spectrum Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000012706 support-vector machine Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 25
- 239000000523 sample Substances 0.000 description 31
- 238000010586 diagram Methods 0.000 description 16
- 238000004590 computer program Methods 0.000 description 12
- 239000011241 protective layer Substances 0.000 description 8
- 230000033001 locomotion Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006378 damage Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 239000010410 layer Substances 0.000 description 3
- 239000004698 Polyethylene Substances 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- -1 cartons Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 229920000573 polyethylene Polymers 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 239000004800 polyvinyl chloride Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A terahertz wave-based internal defect imaging method, an electronic device, and a computer-readable storage medium, the method comprising: obtaining a plurality of terahertz reflection waves reflected back by performing terahertz wave scanning detection on a plurality of detection points of a product to be detected; extracting waveform characteristic parameters of a plurality of terahertz reflected waves; inputting waveform characteristic parameters of the terahertz reflected waves into a defect identification model to obtain a defect detection result and a defect decision value of each detection point; and generating a defect imaging graph based on the defect detection result of each detection point, and generating a defect position decision graph based on the defect decision value of each detection point. According to the invention, the terahertz wave is used for realizing the imaging of the internal defects of the product to be detected, the defect detection accuracy is high, and the severity of the internal defects can be determined.
Description
Technical Field
The invention relates to the technical field of product detection, in particular to an internal defect imaging method based on terahertz waves, electronic equipment and a computer readable storage medium.
Background
In the production and processing of products, defects of different degrees may occur in the products due to processing techniques or processing equipment. At present, the defect detection of products is generally carried out by manual observation or automatic identification after photographing by adopting image equipment, but the defect in the product is difficult to distinguish by the mode.
Taking the product to be detected as a high-voltage insulated cable as an example, the outer sheath may be damaged to different degrees to cause air gaps to appear on the outer sheath, resulting in internal defects. The existence of internal defects of the outer protective layer leads to the reduction of the insulation resistance of the aluminum sheath to the ground, and leads to the multipoint grounding of the metal sheath and the generation of circulation. Internal defects of the outer protective layer may cause the metal protective layer to lose protection and be susceptible to the external environment, resulting in corrosion of the metal protective layer. When the metal sheath is corroded to the penetration hole, it is difficult to prevent moisture from entering the main insulation layer, which may cause the cable to be broken down and the line to stop running. In the actual inspection process, it is often desirable to locate possible internal defects and evaluate the severity of the internal defects without damaging the outer sheath. The currently adopted fault location method for the outer protective layer mainly comprises a step voltage method, a direct current impact method, an audio method and the like, but on one hand, the methods may damage the cable protective layer, on the other hand, the methods are only suitable for locating the outer protective layer under the condition that the outer protective layer has faults, and the severity of the faults cannot be intuitively obtained.
Disclosure of Invention
In view of the above, there is a need for providing an internal defect imaging method based on terahertz waves, an electronic device and a computer readable storage medium, which can detect a product to be detected by terahertz waves, can image internal defects of the product to be detected, and can determine the severity of the internal defects.
An embodiment of the present invention provides a terahertz wave-based internal defect imaging method, including: obtaining a plurality of terahertz reflection waves reflected back by performing terahertz wave scanning detection on a plurality of detection points of a product to be detected; extracting waveform characteristic parameters of the plurality of terahertz reflected waves; inputting the waveform characteristic parameters of the terahertz reflected waves into a defect recognition model trained in advance to obtain a defect detection result and a defect decision value of each detection point in the detection points; and generating a defect imaging graph of the product to be detected based on the defect detection result of each detection point, and generating a defect position decision graph of the product to be detected based on the defect decision value of each detection point.
In some embodiments, the extracting of the waveform characteristic parameter of the terahertz reflected wave includes: performing time domain analysis on the terahertz reflected wave, and extracting time domain spectrum information of the terahertz reflected wave, wherein the time domain spectrum information comprises at least one of a peak value of a waveform, propagation time corresponding to the peak value of the waveform, and an envelope area of the waveform; and performing frequency domain analysis on the terahertz reflected wave, and extracting frequency domain spectrum information of the terahertz reflected wave, wherein the frequency domain spectrum information comprises at least one of amplitude integral of a waveform and energy integral of the waveform.
In some embodiments, the method further comprises: acquiring a plurality of training sample waveforms, wherein the plurality of training sample waveforms comprise terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample containing a defect and terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample not containing the defect, and the product sample containing the defect comprises a plurality of defect types; extracting a waveform characteristic parameter of each training sample waveform in the plurality of training sample waveforms; performing normalization processing and weight distribution on the waveform characteristic parameters of each training sample waveform, and calibrating according to the defect type; and training the waveform characteristic parameters of each training sample waveform based on a support vector machine algorithm and to obtain the defect identification model, wherein the support vector machine algorithm is used for mapping the waveform characteristic parameters of each training sample waveform to a high-dimensional characteristic space through a preset kernel function so as to find a hyperplane to separate two types of product samples in the high-dimensional characteristic space.
In some embodiments, the preset kernel function comprises one of a gaussian kernel function, a linear kernel function, a polynomial kernel function, a laplacian kernel function, a Sigmoid kernel function.
In some embodiments, the inputting the waveform characteristic parameters of the terahertz reflected waves into a defect identification model to obtain a defect detection result and a defect decision value of each of the detection points includes: inputting waveform characteristic parameters corresponding to a first detection point in the detection points into the defect identification model to obtain the relative position relation between the first detection point and the hyperplane; obtaining a defect detection result of the first detection point based on the relative position relation between the first detection point and the hyperplane; and acquiring the relative distance between the first detection point and the hyperplane, and obtaining a defect decision value of the first detection point based on the relative distance.
In some embodiments, the defect detection result includes whether a defect exists and a defect type.
In some embodiments, the acquiring a plurality of terahertz reflected waves reflected back by performing terahertz scanning detection on a plurality of detection points of a product to be detected includes: collecting a plurality of terahertz reflection waves reflected back by performing terahertz wave scanning detection on a plurality of detection points of a product to be detected, and storing waveform data of the terahertz reflection waves to a preset storage area; and reading waveform data of the plurality of terahertz reflected waves from the preset storage area.
In some embodiments, the obtaining a plurality of terahertz reflection waves reflected back by performing terahertz scanning detection on a plurality of detection points of the product to be detected includes: configuring a simulated working environment of the cable to be tested, wherein the simulated working environment comprises a preset temperature and a preset humidity; and acquiring a plurality of terahertz reflected waves reflected by a plurality of detection points of the cable to be detected for performing terahertz wave scanning detection in the simulated working environment.
An embodiment of the invention provides an electronic device, which includes a processor and a memory, where the memory is used for storing instructions, and the processor is used for calling the instructions in the memory, so that the electronic device executes the terahertz wave-based internal defect imaging method.
An embodiment of the present invention provides a computer-readable storage medium storing computer instructions that, when executed on an electronic device, cause the electronic device to perform the above-mentioned terahertz wave-based internal defect imaging method.
Compared with the prior art, the terahertz wave-based internal defect imaging method, the electronic device and the computer-readable storage medium have the advantages of high detection speed, high accuracy, no harm to a detected product and the like by utilizing the terahertz wave to perform nondestructive detection, internal defect imaging is realized by performing time domain and frequency domain waveform analysis on the terahertz reflected wave reflected by the product to be detected, information such as the size, the type, the severity and the like of an internal defect can be visually obtained based on a defect imaging graph and a defect position decision graph obtained by imaging, and risk assessment on the internal defect of the product is facilitated.
Drawings
FIG. 1 is a schematic diagram of an internal defect imaging system according to an embodiment of the present invention.
FIG. 2 is a block diagram of an inspection platform according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating steps of a terahertz wave-based internal defect imaging method according to an embodiment of the present invention.
FIG. 4a is a defect image of a product under test according to an embodiment of the invention.
FIG. 4b is a diagram illustrating a defect location decision diagram of a product under test according to an embodiment of the invention.
Fig. 5 is a functional block diagram of an internal defect imaging apparatus according to an embodiment of the present invention.
Fig. 6 is a functional block diagram of an electronic device according to an embodiment of the present invention.
Description of the main elements
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and detailed description. In addition, the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth to provide a thorough understanding of the present application, and the described embodiments are merely a subset of the embodiments of the present application, rather than all embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It is further noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this application, "at least one" means one or more, and "a plurality" means two or more than two. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, e.g., A and/or B may represent: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. The terms "first," "second," "third," "fourth," and the like in the description and in the claims and drawings of the present application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
In the embodiments of the present application, words such as "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
Fig. 1 is a schematic structural diagram of an internal defect imaging system based on terahertz waves according to a preferred embodiment of the present invention.
The internal defect imaging system 1 includes an electronic device 100, a product 200 to be tested, a terahertz wave generating device 300, and a detection platform 400. The terahertz wave generating device 300 can be used to generate terahertz waves that can be incident on the product 200 to be measured, and the terahertz wave generating device 300 can also collect terahertz waves that are reflected back by the product 200 to be measured. In some embodiments, a collecting device may also be disposed by the detection platform 400 to collect the terahertz reflected wave reflected back via the product 200 to be detected.
In some embodiments, terahertz waves refer to electromagnetic waves with a frequency between 0.1THz and 10THz, and have a wavelength of 0.03mm to 3mm, and have the following excellent physical properties: (1) transient property: typical terahertz pulse width is in picosecond magnitude, and time-resolved transient spectrum research can be conveniently carried out on various materials; (2) low energy performance: compared with electromagnetic waves of other frequency bands, terahertz photon energy is lower (millielectron volts), and compared with X rays, terahertz radiation cannot damage detected substances due to ionization, so that terahertz waves can be used for nondestructive detection of materials; (3) penetrability: terahertz waves have strong penetrating power for a plurality of nonpolar substances and dielectric materials, such as cartons, ceramics, cloth, plastics and the like, and can be used for detecting opaque objects. For example, the product 200 to be tested is a high-voltage insulated cable, and since the sheath layer of the high-voltage insulated cable is generally made of polyvinyl chloride (PVC) or Polyethylene (PE), the method is suitable for detecting the internal defects of the sheath layer by using the terahertz wave technology.
The electronic device 100 may be configured to obtain a terahertz reflected wave reflected back by the product 200 to be detected, and process the terahertz reflected wave to obtain a visual defect image of the product 200 to be detected, where the visual defect image may include a defect imaging map and a defect position decision map, and the defect imaging map and the defect position decision map may be two-dimensional images. The detection platform 400 can be used to construct a detection environment of the product 200 to be detected, so as to simulate working environments of the product 200 to be detected under different temperatures and humidities. As shown in fig. 2, the testing platform 400 may include a sealed test chamber 401 having a temperature and humidity setting function and a three-dimensional moving platform 402. The product 200 to be tested and the terahertz wave generating device 300 can also be disposed in the inspection platform 400.
In an embodiment, the terahertz wave generating device 300 may be a T-Ray 5000 terahertz time-domain spectroscopy system (T-Gauge terahertz time-domain spectroscopy system) which can generate a pulse wave with a frequency of 0-5THz, and the operating mode thereof includes two modes of transmission and reflection, and based on the transmission mode, the terahertz wave is difficult to penetrate through the whole product 200 to be tested, so the reflection mode is preferably adopted, and the time-domain information contained in the reflected wave is richer, and the interface condition of the product 200 to be tested can be reflected better. When defect imaging detection is carried out, the distance between the terahertz probe and the product 200 to be detected can be adjusted to be close to the focal length. The three-dimensional motion platform 402 comprises an X axis, a Y axis and a Z axis, and can support motion in three dimensions of space, the three-dimensional motion platform 402 can comprise a clamp used for clamping the product 200 to be tested, and then the product 200 to be tested can be moved in the X axis, the Y axis and the Z axis directions. Through adjusting the movement in the Z-axis direction, the product 200 to be detected can be located at the focal length of the terahertz probe, and through adjusting the movement in the X-axis direction and the Y-axis direction, terahertz responses at different positions of the product 200 to be detected can be acquired.
According to the terahertz wave generating device, the product 200 to be detected can be scanned by the terahertz wave generating device 300 and the three-dimensional motion platform 402, terahertz reflected wave data can be collected, and the collected terahertz reflected wave data can be analyzed through the electronic equipment 100 to perform defect imaging.
In an embodiment, taking the product 200 to be tested as a power cable as an example, the power cable may have defects inside the cable, including air gaps, holes, cracks and other defects, due to collision, substandard production process, misoperation and other reasons, and the defects are difficult to identify from the appearance. According to the method and the device, the internal defect imaging of the power cable is carried out by utilizing the terahertz wave technology, the internal defect imaging of the power cable is realized by analyzing the terahertz reflected wave, the severity of the defect can be visually shown through the defect position decision diagram, then the working state and the performance of the power cable can be evaluated according to the imaging result, and the possibility of faults and even serious power accidents is effectively reduced.
In one embodiment, the electronic device 100 is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a Processor, a Micro Controller Unit (MCU), an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The electronic device may be a portable electronic device (e.g., a cell phone, a tablet), a personal computer, an industrial computer, a server, etc.
FIG. 3 is a flowchart illustrating steps of an embodiment of a terahertz wave-based internal defect imaging method according to the present application. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.
Referring to fig. 3, the terahertz wave-based internal defect imaging method may include the following steps.
Step S31, acquiring a plurality of terahertz reflection waves reflected back by performing terahertz scanning detection on a plurality of detection points of the product 200 to be detected.
In some embodiments, the three-dimensional motion platform 402 and the terahertz wave generating device 300 are used to scan the product 200 to be tested point by point and collect the terahertz wave reflected by the product 200 to be tested. For example, the product 200 to be measured is a power cable with a preset length, before defect detection is performed on the power cable, the temperature of the detection platform 400 may be set to be a preset temperature, the humidity is set to be a preset humidity, and when the terahertz probe of the terahertz wave generating device 300 scans the plurality of detection points of the power cable, the terahertz wave generating device 300 may collect terahertz waves reflected back through the outer sheath and the aluminum sheath of the power cable. The terahertz reflected wave can be selected as a terahertz time-domain reflected wave.
In some embodiments, when the terahertz wave generating apparatus 300 collects the terahertz reflected wave by the terahertz probe, the waveform data of the collected terahertz reflected wave may be transmitted to the electronic device 100 for analysis. The terahertz wave generating device 300 may also store the acquired waveform data of the terahertz reflected wave to a preset storage area first. The preset storage area may be a storage area on the electronic device 100 or may be a storage area independent from the electronic device 100. When waveform data analysis is required, the electronic apparatus 100 reads the waveform data of the terahertz reflected wave from the preset storage region again.
And step S32, extracting the waveform characteristic parameters of the plurality of terahertz reflected waves.
In some embodiments, the waveform characteristic parameters may be obtained by performing waveform characteristic extraction of a time domain spectrum and a frequency domain spectrum on each terahertz reflected wave. The waveform characteristic parameters may include one or more of a peak of the waveform, a propagation time corresponding to the peak of the waveform, an envelope area of the waveform, an amplitude integral of the waveform, and an energy integral of the waveform.
For example, the terahertz reflected wave is a terahertz time-domain reflected wave, and the time-domain analysis can be directly performed on the terahertz time-domain reflected wave to extract time-domain spectrum information of the terahertz time-domain reflected wave. The time domain spectral information may include at least one of a peak of the waveform, a propagation time corresponding to the peak of the waveform, and an envelope area of the waveform. When the waveform characteristics of the frequency domain spectrum are extracted, the terahertz time-domain reflected wave can be subjected to Fourier transform to obtain the terahertz frequency-domain reflected wave, and the frequency domain spectrum information of the terahertz frequency-domain reflected wave is extracted by performing frequency domain analysis on the terahertz frequency-domain reflected wave. The frequency domain spectral information may include at least one of an amplitude integral of the waveform, an energy integral of the waveform.
The waveform characteristic parameters are extracted in a time domain slicing mode, a frequency domain slicing mode and an integral mode, and compared with the traditional terahertz wave imaging mode, the terahertz wave characteristic parameters need to be manually positioned and preanalyzed, so that the terahertz wave imaging process is greatly simplified.
Step S33, inputting the waveform characteristic parameters of the terahertz reflected waves into a defect recognition model trained in advance, and obtaining a defect detection result and a defect decision value of each detection point in the detection points.
In some embodiments, the defect identification model may be obtained by selecting a corresponding machine learning algorithm for training according to actual requirements, which is not limited in the present application. For example, the defect recognition model may be trained by using a Support Vector Machines (SVM) algorithm. The following example illustrates a defect recognition model obtained by training based on an SVM algorithm: a) acquiring a plurality of training sample waveforms, wherein the number of the training sample waveforms can be set according to the training requirements of an actual model, and the method is not limited in this application, for example, acquiring 3600 training sample waveforms, wherein the 3600 training sample waveforms include terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample containing a defect and terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample not containing the defect, wherein the product sample containing the defect includes a plurality of defect types, that is, terahertz reflected waves of samples of various defect types and normal samples are acquired as training data, and the training data can be divided into a training set and a test set, for example, the number ratio of the training set to the test set is 8: 2; b) extracting waveform characteristic parameters of each of a plurality of training sample waveforms, e.g., the waveform characteristic parameters include five characteristic parameters: the peak value of the waveform, the propagation time corresponding to the peak value of the waveform, the envelope area of the waveform, the amplitude integral of the waveform and the energy integral of the waveform; the waveform characteristic parameters of each training sample waveform are normalized and weight-distributed, and are calibrated according to the defect types, and the weight distribution proportion of the five characteristic parameters can be set according to the actual training effect of the model, for example, the weight distribution proportion of the peak value of the waveform, the propagation time corresponding to the peak value of the waveform, the envelope area of the waveform, the amplitude integral of the waveform and the energy integral of the waveform is as follows: 1:0.8:0.6:0.7: 0.7; c) and training the waveform characteristic parameters of each training sample waveform in the training set based on a support vector machine algorithm to obtain a defect identification model, wherein the support vector machine algorithm is used for mapping the waveform characteristic parameters of each training sample waveform to a high-dimensional characteristic space through a preset kernel function so as to find a hyperplane to separate two types of product samples (defect product samples and normal product samples) in the high-dimensional characteristic space.
In some embodiments, the preset kernel function may be selected according to actual requirements, for example, the preset kernel function is a gaussian kernel function. And mapping the classification function to a high-dimensional feature space through a Gaussian kernel function to find an optimal hyperplane. The optimal hyperplane can be expressed by the following linear equation: w is aTx + b is 0, wherein wTB is a predetermined constant. The gaussian kernel function can be expressed as:
wherein x is1Is any point in space, x2Is the kernel center and σ is the width parameter of the kernel.
In some embodiments, the preset kernel function may also be a linear kernel, a polynomial kernel, a laplacian kernel, a Sigmoid kernel function, or the like.
In some embodiments, the objective function of the optimal hyperplane may be expressed as:
w is an optimal hyperplane coefficient, C is a penalty parameter, the larger the value of C is, the larger the penalty to classification is, and xi isiFor the relaxation variables, each sample has a corresponding relaxation variable characterizing the extent to which the sample does not satisfy the constraint.
In some embodiments, the model parameters may be adjusted according to whether the defect image obtained by the subsequent conversion is clear or not and whether the accuracy of defect identification meets the preset requirement or not, and the adjustment of the model parameters may include adjustment of a support vector machine type, adjustment of a kernel function, adjustment of a loss function, and the like.
In some embodiments, the defect detection result of the detection point may include whether a defect exists and a defect type of the detection point when the defect exists. The defect decision value of the detection point can represent the probability that the detection point is a defect, the larger the decision value is, the higher the probability that the point is a defect point is, and the defect decision value imaging can better reflect the boundary condition of the defect part and the normal part of the product.
In some embodiments, when the defect recognition model meeting the requirement is obtained through training, the waveform characteristic parameters of the terahertz reflected wave of the product 200 to be detected may be input to the defect recognition model, so as to obtain the defect detection result and the defect decision value at each detection point. Taking a first detection point of the plurality of detection points on the product 200 to be detected as an example, the waveform characteristic parameter corresponding to the first detection point is input to the defect identification model, so that the relative position relationship between the first detection point and the hyperplane can be obtained, and further, the defect detection result of the first detection point can be obtained based on the relative position relationship between the first detection point and the hyperplane. The relative distance between the first detection point and the hyperplane can be obtained through the defect identification model, and then the defect decision value of the first detection point can be obtained based on the relative distance.
Step S34, generating a defect imaging map of the product 200 to be tested based on the defect detection result of each detection point, and generating a defect position decision map of the product 200 to be tested based on the defect decision value of each detection point.
In some embodiments, when the defect detection results of the plurality of detection points are obtained, the corresponding defect imaging map may be generated based on the defect detection results of the plurality of detection points. When the defect decision values of the plurality of detection points are obtained, a corresponding defect position decision map may be generated based on the defect decision values of the plurality of detection points. For example, the defect detection result of the detection point is a defect label matrix output by the defect identification model, and the defect label matrix can be converted into a two-dimensional defect imaging map by adopting the existing imaging program; the defect decision value of the detection point is a defect probability matrix output by the defect identification model, and the defect probability matrix can be converted into a two-dimensional defect position decision diagram by adopting the conventional imaging program.
Fig. 4a is a defect imaging diagram of the product 200 to be tested, and assuming that the appearance of the internal defect of the product 200 to be tested is a five-pointed star shape, the color region Co1 indicates the position identified as having a defect, and the color region Co2 indicates the position identified as normal. Fig. 4b is a defect position decision diagram of the product 200 to be tested, the size of the defect decision value V1 represents the probability that a detection point is a defect, the larger the defect decision value V1 is, the higher the probability that the detection point is a defect point is, and the situation of the boundary between the defect area and the normal area can be better reflected by the defect position decision diagram of fig. 4 b. The problem that the characteristics of the scanning point are difficult to accurately represent due to the fact that the waveform characteristics of the junction of the defect and the normal sample are not obvious, the waveform detected by the terahertz wave can be located between the normal sample and the defect sample at the same time and the waveform changes along with the change of the area ratio of the light spot at the defect and the area ratio of the defect-free position is solved, the condition of the junction of the defect and the normal sample can be better reflected through a defect position decision diagram, and the defect severity of the detection point can be effectively represented.
According to the internal defect imaging method based on the terahertz waves, nondestructive detection is performed by utilizing the terahertz waves, the method has the advantages of high detection speed, high accuracy, no harm to a detected product and the like, internal defect imaging is realized by performing time domain and frequency domain waveform analysis on the terahertz reflected waves reflected back by the product to be detected, information such as the size, type, severity and the like of the internal defects can be visually obtained based on a defect imaging graph and a defect position decision graph obtained by imaging, and risk assessment on the internal defects of the product is facilitated.
Based on the same idea as the terahertz-wave-based internal defect imaging method in the above-described embodiment, the present application also provides an internal defect imaging apparatus that can be used to perform the above-described terahertz-wave-based internal defect imaging method. For convenience of illustration, only the parts related to the embodiments of the present application are shown in the schematic structural diagram of the internal defect imaging apparatus, and those skilled in the art will appreciate that the illustrated structure is not limited to the apparatus, and may include more or less components than those illustrated, or some components may be combined, or different arrangements of components may be used.
As shown in fig. 5, the internal defect imaging apparatus 10 includes an acquisition module 101, an extraction module 102, a processing module 103, and a generation module 104. In some embodiments, the modules may be programmable software instructions stored in a memory and invoked for execution by a processor. It will be appreciated that in other embodiments, the modules may also be program instructions or firmware (firmware) that are resident in the processor.
The obtaining module 101 is configured to obtain a plurality of terahertz reflected waves reflected back by performing terahertz scanning detection on a plurality of detection points of a product to be detected.
An extracting module 102, configured to extract waveform characteristic parameters of a plurality of terahertz reflected waves.
The processing module 103 is configured to input the waveform characteristic parameters of the terahertz reflected waves into a defect identification model trained in advance, so as to obtain a defect detection result and a defect decision value of each detection point in the plurality of detection points.
The generating module 104 is configured to generate a defect imaging graph of the product to be detected based on the defect detection result of each detection point, and generate a defect position decision graph of the product to be detected based on the defect decision value of each detection point.
Fig. 6 is a schematic diagram of an embodiment of an electronic device according to the present application.
The electronic device 100 comprises a memory 20, a processor 30 and a computer program 40 stored in the memory 20 and executable on the processor 30. The processor 30, when executing the computer program 40, implements the steps in the above-described embodiment of the terahertz wave-based internal defect imaging method, such as steps S31 to S34 shown in fig. 3.
Illustratively, the computer program 40 may also be divided into one or more modules/units, which are stored in the memory 20 and executed by the processor 30. The one or more modules/units may be a series of computer program instruction segments capable of performing certain functions, the instruction segments describing the execution of the computer program 40 in the electronic device 100. For example, the system can be divided into the acquisition module 101, the extraction module 102, the processing module 103, and the generation module 104 shown in fig. 5.
Those skilled in the art will appreciate that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation of the electronic device 100, and may include more or fewer components than those shown, or some of the components may be combined, or different components, e.g., the electronic device 100 may further include input-output devices, network access devices, buses, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor, a single chip, or the processor 30 may be any conventional processor or the like.
The memory 20 may be used to store the computer program 40 and/or the module/unit, and the processor 30 may implement various functions of the electronic device 100 by running or executing the computer program and/or the module/unit stored in the memory 20 and calling data stored in the memory 20. The memory 20 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data) created according to the use of the electronic apparatus 100, and the like. In addition, the memory 20 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other non-volatile solid state storage device.
The integrated modules/units of the electronic device 100 may be stored in a computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer readable storage medium, and the steps of the method embodiments described above can be realized when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
In the several embodiments provided in the present application, it should be understood that the disclosed electronic device and method may be implemented in other ways. For example, the above-described embodiments of the electronic device are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions when the actual implementation is performed.
In addition, functional units in the embodiments of the present application may be integrated into the same processing unit, or each unit may exist alone physically, or two or more units are integrated into the same unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Several units or electronic devices recited in the electronic device claims may also be implemented by one and the same unit or electronic device by means of software or hardware. The terms first, second, etc. are used to denote names, but not to denote any particular order.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that modifications or equivalent substitutions may be made to the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.
Claims (10)
1. A terahertz wave-based internal defect imaging method is characterized by comprising the following steps:
obtaining a plurality of terahertz reflection waves reflected back by performing terahertz wave scanning detection on a plurality of detection points of a product to be detected;
extracting waveform characteristic parameters of the plurality of terahertz reflected waves;
inputting the waveform characteristic parameters of the terahertz reflected waves into a defect recognition model trained in advance to obtain a defect detection result and a defect decision value of each detection point in the detection points;
and generating a defect imaging graph of the product to be detected based on the defect detection result of each detection point, and generating a defect position decision graph of the product to be detected based on the defect decision value of each detection point.
2. The terahertz-wave-based internal defect imaging method as claimed in claim 1, wherein the extracting of the waveform characteristic parameters of the terahertz reflected wave comprises:
performing time domain analysis on the terahertz reflected wave, and extracting time domain spectrum information of the terahertz reflected wave, wherein the time domain spectrum information comprises at least one of a peak value of a waveform, propagation time corresponding to the peak value of the waveform, and an envelope area of the waveform;
and performing frequency domain analysis on the terahertz reflected wave, and extracting frequency domain spectrum information of the terahertz reflected wave, wherein the frequency domain spectrum information comprises at least one of amplitude integral of a waveform and energy integral of the waveform.
3. The terahertz-wave-based internal defect imaging method according to claim 1 or 2, further comprising:
acquiring a plurality of training sample waveforms, wherein the plurality of training sample waveforms comprise terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample containing a defect and terahertz reflected waves reflected by performing terahertz wave scanning detection on a product sample not containing the defect, and the product sample containing the defect comprises a plurality of defect types;
extracting a waveform characteristic parameter of each training sample waveform in the plurality of training sample waveforms;
performing normalization processing and weight distribution on the waveform characteristic parameters of each training sample waveform, and calibrating according to the defect type;
and training the waveform characteristic parameters of each training sample waveform based on a support vector machine algorithm and to obtain the defect identification model, wherein the support vector machine algorithm is used for mapping the waveform characteristic parameters of each training sample waveform to a high-dimensional characteristic space through a preset kernel function so as to find a hyperplane to separate two types of product samples in the high-dimensional characteristic space.
4. The terahertz-wave-based internal defect imaging method according to claim 3, wherein the preset kernel function includes one of a Gaussian kernel function, a linear kernel function, a polynomial kernel function, a Laplace kernel function, and a Sigmoid kernel function.
5. The terahertz-wave-based internal defect imaging method as claimed in claim 3, wherein the inputting the waveform characteristic parameters of the plurality of terahertz reflected waves into a defect recognition model to obtain a defect detection result and a defect decision value for each of the plurality of detection points comprises:
inputting waveform characteristic parameters corresponding to a first detection point in the detection points into the defect identification model to obtain the relative position relation between the first detection point and the hyperplane;
obtaining a defect detection result of the first detection point based on the relative position relation between the first detection point and the hyperplane;
and acquiring the relative distance between the first detection point and the hyperplane, and obtaining a defect decision value of the first detection point based on the relative distance.
6. The terahertz-wave-based internal defect imaging method as claimed in claim 3, wherein the defect detection result includes presence or absence of a defect and a defect type.
7. The terahertz-wave-based internal defect imaging method as claimed in claim 1, wherein the acquiring of the plurality of terahertz reflected waves reflected back by performing terahertz-wave scanning detection on the plurality of detection points of the product under test comprises:
collecting a plurality of terahertz reflection waves reflected back by performing terahertz wave scanning detection on a plurality of detection points of a product to be detected, and storing waveform data of the terahertz reflection waves to a preset storage area;
waveform data of the plurality of terahertz reflected waves is read from the preset storage region.
8. The terahertz-wave-based internal defect imaging method as claimed in claim 1, wherein the product under test is a cable under test, and the acquiring of the plurality of terahertz reflected waves reflected back by performing terahertz-wave scanning detection on the plurality of detection points of the product under test comprises:
configuring a simulated working environment of the cable to be tested, wherein the simulated working environment comprises a preset temperature and a preset humidity;
and acquiring a plurality of terahertz reflected waves reflected by a plurality of detection points of the cable to be detected for performing terahertz wave scanning detection in the simulated working environment.
9. An electronic device comprising a processor and a memory, wherein the memory is used for storing instructions, and the processor is used for calling the instructions in the memory so as to enable the electronic device to execute the terahertz wave-based internal defect imaging method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that it stores computer instructions that, when run on an electronic device, cause the electronic device to perform the terahertz wave-based internal defect imaging method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210302242.0A CN114689598A (en) | 2022-03-24 | 2022-03-24 | Terahertz wave-based internal defect imaging method, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210302242.0A CN114689598A (en) | 2022-03-24 | 2022-03-24 | Terahertz wave-based internal defect imaging method, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114689598A true CN114689598A (en) | 2022-07-01 |
Family
ID=82138864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210302242.0A Pending CN114689598A (en) | 2022-03-24 | 2022-03-24 | Terahertz wave-based internal defect imaging method, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114689598A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116818704A (en) * | 2023-03-09 | 2023-09-29 | 苏州荣视软件技术有限公司 | High-precision full-automatic detection method, equipment and medium for semiconductor flaw AI |
-
2022
- 2022-03-24 CN CN202210302242.0A patent/CN114689598A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116818704A (en) * | 2023-03-09 | 2023-09-29 | 苏州荣视软件技术有限公司 | High-precision full-automatic detection method, equipment and medium for semiconductor flaw AI |
| CN116818704B (en) * | 2023-03-09 | 2024-02-02 | 苏州荣视软件技术有限公司 | High-precision full-automatic detection method, equipment and medium for semiconductor flaw AI |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103528617B (en) | A kind of cockpit instrument identifies and detection method and device automatically | |
| JP6476861B2 (en) | Electromagnetic field feature classification presentation device | |
| CN112465077B (en) | Fruit sugar degree nondestructive detection method and device, computer equipment and storage medium | |
| CN111044570A (en) | Defect identification and early warning method and device for power equipment and computer equipment | |
| CN114689598A (en) | Terahertz wave-based internal defect imaging method, electronic device, and storage medium | |
| CN106384116A (en) | Terahertz imaging based plant vein recognition method and device | |
| CN111879709B (en) | Lake water body spectral reflectivity inspection method and device | |
| CN116958036A (en) | Method for inspecting pollution state of insulator by unmanned aerial vehicle based on hyperspectral technology | |
| US10775349B2 (en) | Defect detection using ultrasound scan data | |
| CN111965167A (en) | Method and device for predicting element composition and calorific value of solid waste | |
| CN111523587A (en) | Woody plant species spectrum identification method based on machine learning | |
| Ghanizadeh et al. | Application of characteristic impedance and wavelet coherence technique to discriminate mechanical defects of transformer winding | |
| CN110579483B (en) | Terahertz wave-based internal defect imaging device and method and readable storage medium | |
| EP3526768A1 (en) | Processing digital image to remove unwanted portion | |
| CN114494765B (en) | Method and device for identifying true and false smoke discrimination points, electronic equipment and storage medium | |
| Serpaud et al. | Sequential adaptive sampling algorithm to reduce the near-field measurement time | |
| CN112928988B (en) | Accelerated aging test method and system for photovoltaic module | |
| CN113075159B (en) | Terahertz spectrum-based cell imaging system for slice inspection | |
| Bickler | Prospects for machine learning for shell midden analysis | |
| Qian et al. | Deep Learning-Augmented Stand-off Radar Scheme for Rapidly Detecting Tree Defects | |
| Cui et al. | Defocusing recovery technology of terahertz image based on 3-D PSF simulations | |
| CN113222908B (en) | Hyperspectral shielding effect evaluation method based on self-adaptive spectrum band screening network | |
| Brand et al. | Advances in high-resolution non-destructive defect localization based on Machine Learning enhanced signal processing | |
| Han et al. | Non-destructively qualitative and quantitative inspection methods based on THz spectroscopy and imaging | |
| CN118279672A (en) | Image detection method and system for fuel rod assembly in nuclear power station pool |
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 |