CN113624804A - Nondestructive testing method and system for additive manufacturing component - Google Patents
Nondestructive testing method and system for additive manufacturing component Download PDFInfo
- Publication number
- CN113624804A CN113624804A CN202110818533.0A CN202110818533A CN113624804A CN 113624804 A CN113624804 A CN 113624804A CN 202110818533 A CN202110818533 A CN 202110818533A CN 113624804 A CN113624804 A CN 113624804A
- Authority
- CN
- China
- Prior art keywords
- laser
- information
- defect
- additively manufactured
- additive manufacturing
- 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
- 239000000654 additive Substances 0.000 title claims abstract description 87
- 230000000996 additive effect Effects 0.000 title claims abstract description 87
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000009659 non-destructive testing Methods 0.000 title claims abstract description 30
- 230000007547 defect Effects 0.000 claims abstract description 82
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 230000005284 excitation Effects 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000008054 signal transmission Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000002604 ultrasonography Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 2
- 230000007774 longterm Effects 0.000 claims 1
- 230000008859 change Effects 0.000 description 9
- 238000001931 thermography Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 230000001066 destructive effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 239000002184 metal Substances 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 239000007822 coupling agent Substances 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000032798 delamination Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005204 segregation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 238000010301 surface-oxidation reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- 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
- G01N21/1702—Systems in which incident light is modified in accordance with the properties of the material investigated with opto-acoustic detection, e.g. for gases or analysing solids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- 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
- G01N21/1702—Systems in which incident light is modified in accordance with the properties of the material investigated with opto-acoustic detection, e.g. for gases or analysing solids
- G01N2021/1706—Systems in which incident light is modified in accordance with the properties of the material investigated with opto-acoustic detection, e.g. for gases or analysing solids in solids
-
- 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
- G06T2207/10048—Infrared 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention belongs to the technical field of nondestructive testing, and discloses a nondestructive testing method and system for an additive manufacturing component. The method comprises the steps of thermally exciting the surface of the additive manufacturing component by using a laser as an ultrasonic excitation source, collecting an infrared image of the additive manufacturing component through an infrared detection module to respectively obtain background information and surface temperature information, determining the position of a defect based on the image information of the background subtraction, and obtaining a mapping relation between the defect temperature information and the defect size information by using an LSTM neural network to realize size prediction of the defect of the additive manufacturing component. The system comprises a laser ultrasonic excitation module, an infrared detection module and a control processing module. The invention can realize non-contact high-precision defect detection of the additive manufacturing component.
Description
Technical Field
The invention belongs to the technical field of nondestructive testing, and particularly relates to a nondestructive testing method and system for an additive manufacturing component.
Background
The metal additive manufacturing can realize the rapid forming of large components with complex structures and has the advantages of short processing period and high efficiency. However, the additive manufacturing process of the component has the defects of severe raw material reaction process, complex temperature change, unpredictable molten pool condition and the like in the final product. The defects of the additive manufacturing component are roughly classified into: surface defects and internal defects. The surface defects comprise surface roughness, surface cracks, surface oxidation, spheroidization and the like, and the internal defects comprise macro cracks, unfused inclusions, holes (generally with the size of several micrometers to several hundred micrometers), microcracks, alloy element segregation and the like caused by internal stress. The defects finally affect the physical and chemical properties of the part and weaken the mechanical properties of the part, and limit the popularization of metal additive manufacturing technology and the industrial application of metal additive manufacturing components, so that the quality evaluation or detection of the metal additive manufacturing components is particularly important. The infrared wave nondestructive detection technology is provided from the 70 th of the 20 th century, and has wide application fields, such as aerospace, energy transportation, new materials and the like, and the defect types of detection comprise cracks, delamination, debonding and the like. The technology mainly adopts active excitation to detect the defects of the detected material, specifically, the excitation causes the temperature change at the material defects, and then the change of the observed temperature field is recorded by a thermal infrared imager. For thermal excitation sources, there are currently ultrasound, laser, flash lamps, etc. The means of ultrasonic excitation include the use of piezoelectric transducers, electromagnetic transducers, air-coupled ultrasonic transducers, and capacitive transducers. In which the piezoelectric transducer is of the contact type, a coupling agent has to be added between the component and the probe, which is not permissible for inspection environments with special requirements, such as additive manufacturing processes. In addition, it is also a great challenge for the contact piezoelectric transducer to excite ultrasonic waves in a high-temperature and high-pressure environment. For the other three non-contact transducers, the energy conversion efficiency is rapidly attenuated along with the increase of the distance between the component and the probe, wherein the lift-off height of electromagnetic ultrasound needs to be controlled within 1mm, so that the additive manufacturing component cannot be remotely excited, and the non-contact transducer is not suitable for nondestructive detection of the additive manufacturing component. Therefore, how to realize nondestructive testing of an additive manufacturing component at a longer distance and further predict or identify the defect size is a problem to be solved in the art.
Disclosure of Invention
The invention provides a nondestructive testing method and a nondestructive testing system for an additive manufacturing component, and solves the problem that non-contact high-precision defect detection of the additive manufacturing component cannot be realized in the prior art.
The invention provides a nondestructive testing method of an additive manufacturing component, which comprises the following steps of;
acquiring an infrared image of the additive manufacturing component through an infrared detection module to obtain background information;
the method comprises the following steps of thermally exciting the surface of the additive manufacturing component by using a laser as an ultrasonic excitation source, and acquiring an infrared image of the additive manufacturing component through an infrared detection module to obtain surface temperature information;
subtracting the background information from the surface temperature information to obtain processed image information;
performing temperature gradient operation on the processed image information, and determining the position of a defect according to the obtained surface temperature gradient distribution information of the additive manufacturing component;
extracting characteristic temperature corresponding to the defect position from each frame of image of the processed image information to form characteristic temperature-time information;
constructing a data set based on the characteristic temperature-time information, and dividing the data set into a training set and a testing set;
constructing an LSTM neural network, and respectively training and testing the LSTM neural network by using the training set and the test set to obtain a trained neural network model;
and predicting the size of the defect of the additive manufacturing component by using the trained neural network model.
Preferably, the LSTM neural network is configured to obtain a mapping relationship between defect temperature information and defect size information.
Preferably, the LSTM neural network includes an input layer, an LSTM network layer, a first fully-connected layer, a discard layer, a second fully-connected layer, and a regression layer;
the input layer is used for inputting the characteristic temperature-time information;
the LSTM network layer is used for processing the characteristic temperature-time information with a long time so as to avoid long-time dependence;
the first full-connection layer is used for connecting neurons between layers and capturing defect information;
the abandon layer is used for randomly screening and removing part of neurons so as to prevent overfitting of the training set;
the second full-connection layer is used for connecting the neurons left after screening so as to better capture defect information;
the regression layer is used for predicting the size of the defect based on the defect information.
Preferably, the number of samples is expanded by adjusting the parameters of the laser when constructing the data set; the parameters of the laser include power, wavelength, and pulse width.
Preferably, the defects include cracks and holes.
In another aspect, the present invention provides a non-destructive inspection system for an additive manufactured component, comprising: the device comprises a laser ultrasonic excitation module, an infrared detection module and a control processing module;
the laser ultrasonic excitation module is used for thermally exciting the surface of the additive manufacturing component;
the infrared detection module is used for collecting an infrared image of the additive manufacturing component;
the control processing module is used for realizing the steps of image processing and defect size prediction in the nondestructive testing method of the additive manufacturing component.
Preferably, the laser ultrasonic excitation module comprises a pulse laser, a laser path unit and a laser head; the pulse laser is connected with the laser head through the laser light path unit;
the infrared detection module comprises a thermal infrared imager, a thermal signal transmission cable and an infrared camera; the thermal infrared imager is connected with the infrared camera through the thermal signal transmission cable;
the control processing module comprises a computer; and the computer is respectively connected with the thermal infrared imager and the pulse laser.
Preferably, the light source emitted by the pulse laser comprises a linear light source and a point light source, and the focusing of the laser light source is realized through a lens.
Preferably, the control processing module further includes: a pick head motion control mechanism; the computer is connected with the collecting head motion control mechanism, and the collecting head motion control mechanism controls the infrared camera and the laser head to move through a mechanical arm.
Preferably, the non-destructive inspection system for an additive manufactured component further comprises: an object stage; an additive manufacturing component is placed on the stage, the additive manufacturing component being placed below the laser head.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
in the method, under the condition that a laser does not work, an infrared detection module is used for collecting an infrared image of the additive manufacturing component to obtain background information; then, a laser is used as an ultrasonic excitation source to thermally excite the surface of the additive manufacturing component, and an infrared detection module is used for collecting an infrared image of the additive manufacturing component to obtain surface temperature information; then subtracting the background information from the surface temperature information to obtain processed image information so as to eliminate the influence of the environment on the detection effect; the processed image information is transmitted to a control processing module, temperature gradient operation is carried out on the processed image information, and the position of the defect is determined according to the obtained surface temperature gradient distribution information of the additive manufacturing component; extracting characteristic temperature corresponding to the defect position from each frame of image in the processed image information to form characteristic temperature-time information; constructing a data set based on the characteristic temperature-time information, and dividing the data set into a training set and a testing set; constructing an LSTM neural network, and respectively training and testing the LSTM neural network by utilizing a training set and a testing set to obtain a trained neural network model; and finally, predicting the size of the defect of the additive manufacturing component by using the trained neural network model. The laser is used as an ultrasonic excitation source to thermally excite the surface of the additive manufacturing component, so that the additive manufacturing component can be remotely excited, the mapping relation between the defect temperature information and the defect size information is obtained by using the LSTM neural network, and the size of the defect of the additive manufacturing component can be predicted or identified.
Drawings
Fig. 1 is a schematic flow chart of a nondestructive testing method for an additive manufactured component according to embodiment 1 of the present invention;
FIG. 2 is a flowchart of an LSTM neural network in the nondestructive testing method for an additive manufactured part according to embodiment 1 of the present invention;
fig. 3 is a schematic structural diagram of a nondestructive testing system for an additive manufactured component according to embodiment 2 of the present invention.
The system comprises a pulse laser 1, a thermal infrared imager 2, a laser light path unit 3, a thermal signal transmission cable 4, a computer 5, a pick head motion control mechanism 6, an infrared camera 7, a laser head 8, a laser head 9, an additive manufacturing component 10 and an objective table 10.
Detailed Description
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
embodiment 1 provides a nondestructive testing method of an additive manufactured component, referring to fig. 1, including the steps of;
acquiring an infrared image of the additive manufacturing component through an infrared detection module to obtain background information;
the method comprises the following steps of thermally exciting the surface of the additive manufacturing component by using a laser as an ultrasonic excitation source, and acquiring an infrared image of the additive manufacturing component through an infrared detection module to obtain surface temperature information;
subtracting the background information from the surface temperature information to obtain processed image information;
performing temperature gradient operation on the processed image information, and determining the position of a defect according to the obtained surface temperature gradient distribution information of the additive manufacturing component;
extracting characteristic temperature corresponding to the position of the defect from each frame of image in the processed image information to form characteristic temperature-time information;
constructing a data set based on the characteristic temperature-time information, and dividing the data set into a training set and a testing set;
constructing an LSTM neural network, and respectively training and testing the LSTM neural network by using the training set and the test set to obtain a trained neural network model;
and predicting the size of the defect of the additive manufacturing component by using the trained neural network model.
The LSTM neural network is used for obtaining a mapping relation between defect temperature information and defect size information. Referring to fig. 2, the LSTM neural network includes an input layer, an LSTM network layer, a first fully-connected layer (i.e., fully-connected layer 1 in fig. 2), a discard layer, a second fully-connected layer (i.e., fully-connected layer 2 in fig. 2), and a regression layer. The input layer is used for inputting the characteristic temperature-time information; the LSTM network layer is used for processing the characteristic temperature-time information with a long time so as to avoid long-time dependence; the first full-connection layer is used for connecting neurons between layers and capturing defect information; the abandon layer is used for randomly screening and removing part of neurons so as to prevent overfitting of the training set; the second full-connection layer is used for connecting the neurons left after screening so as to better capture defect information; the regression layer is used for predicting the size of the defect based on the defect information.
Furthermore, the number of samples can be expanded by adjusting the parameters of the laser when constructing the data set; the parameters of the laser include power, wavelength, and pulse width.
The defects in example 1 included cracks and holes.
Example 2:
Referring to fig. 3, the laser ultrasonic excitation module includes a pulse laser 1, a laser optical path unit 3 and a laser head 8; the pulse laser 1 is connected with the laser head 8 through the laser light path unit 3. The infrared detection module comprises a thermal infrared imager 2, a thermal signal transmission cable 4 and an infrared camera 7; the thermal infrared imager 2 is connected with the infrared camera 7 through the thermal signal transmission cable 4. The control processing module comprises a computer 5; and the computer 5 is respectively connected with the thermal infrared imager 2 and the pulse laser 1.
Specifically, the control processing module may further include: a pick head motion control mechanism 6; the computer 5 is connected with the collecting head motion control mechanism 6, and the collecting head motion control mechanism 6 controls the infrared camera 7 and the laser head 8 to move through a mechanical arm.
Furthermore, the non-destructive inspection system of the additive manufactured component further comprises an object stage 10; additive manufacturing components 9 are placed on the object stage 10, and the additive manufacturing components 9 are placed below the laser heads 8
The light source emitted by the pulse laser 1 comprises a linear light source and a point light source, and the focusing of the laser light source is realized through a lens.
The present invention is further described below.
The invention provides a nondestructive testing method and a nondestructive testing system for an additive manufacturing component, and a non-contact high-precision crack detection scheme for the additive manufacturing component mainly comprises the following three aspects.
In the first aspect, for the thermal excitation source ultrasonic wave, a laser is used as an excitation source of the ultrasonic wave. The material absorbs part of energy of the pulse laser irradiated on the surface and converts the energy into heat energy, so that the temperature of the surrounding area is increased to generate thermal expansion, and ultrasonic waves are excited. The ultrasonic wave makes crack defect vibration produce the heat, realizes non-contact detection. Solid-state pulsed lasers are ultrasonic excitation devices. The light source excited by the pulse laser is divided into a laser line light source and a laser point light source, and the laser light source is focused through different lenses. The incidence of different laser sources on the surface of the component excites ultrasonic waves with different propagation characteristics.
In a second aspect, an infrared detection module is adopted to detect the surface temperature of the additive manufacturing component, and image information for eliminating the influence of the ring mirror is obtained through a computer. The thermal infrared imager is enabled to work firstly (at the moment, the laser does not work), the thermal infrared imager obtains an infrared image of the detection member, the image contains information representing the surface temperature of the test piece, and the temperature distribution influenced by the environment can be recorded and used as background information; and after the laser works, receiving the infrared rays radiated by the surface of the component through the lens of the infrared camera again, acquiring heat information of the surface of the component, transmitting the information to the thermal infrared imager, and further drawing a temperature distribution thermal image of the surface of the component to be recorded as surface temperature information. And transmitting the background information and the surface temperature information to a computer, and subtracting the background information from the surface temperature information to obtain processed image information so as to eliminate the influence of the environment mirror on the detection effect.
In a third aspect, prediction or identification of defects is achieved based on an LSTM neural network. The following description will specifically explain the defect as a crack. Improvements in the thermal image processing section are needed to enable detection of micron scale crack defects. The temperature information collected by the thermal infrared imager changes with time. In contrast, the method adopts a long-short term memory (LSTM) network to analyze the time signal so as to obtain the mapping relation between the defect size and the time signal and realize the visualization of the defect size.
Specifically, the step of the temperature characteristic extraction process of the crack position in the third aspect is as follows:
(1) and (3) performing temperature gradient operation on the image with the background subtracted, so that the temperature information difference of each area part is better embodied, and determining the position of the crack through the temperature gradient distribution information of the surface of the component.
(2) Because the background temperature is subtracted from the obtained thermal imaging image, after the crack position in the thermal image is determined, the information such as the characteristic temperature of the crack position and the like can be directly extracted from each frame of thermal imaging image to form a characteristic temperature-time signal which is used as an input value of an LSTM neural network.
The flow of predicting the crack based on the LSTM neural network adopted in the present invention is shown in fig. 2, and includes:
(1) the input layer is used for inputting the obtained characteristic temperature-time signals such as crack temperature and the like;
(2) the LSTM network layer processes a characteristic temperature-time signal with a long time, so that the problem of long-time dependence can be avoided;
(3) a fully connected layer 1 connecting each neuron between layers, thereby capturing information related to a crack;
(4) a abandon layer, which randomly screens one neuron out of the neurons to ensure that the neuron does not participate in training, prevents overfitting of a training set and eliminates the possible influence of environmental noise and the like in the training set;
(5) and a full connection layer 2 for connecting the remaining neurons so as to better capture information about the crack.
(6) And a regression layer for predicting the crack depth and width.
Through the steps, the laser ultrasonic excitation method can excite the surface of the component to generate ultrasonic waves for the micro cracks in the additive manufacturing component through the laser ultrasonic excitation, further cause the cracks to vibrate, rub and generate heat, and then record the heat through the thermal infrared imager to qualitatively detect the defects on the surface of the component. Furthermore, the specific width and depth of the micro-crack are quantitatively predicted by utilizing a neural network training method, and an actual basis is provided for ensuring that the product meets engineering indexes.
The principle of the test of the invention is as follows: the laser controller controls the laser emitting device to emit laser with preset power, when pulse laser reaches the surface of the component, ultrasonic waves are excited due to the action of thermoelastic, the ultrasonic waves propagate in the component, and if the detected component has a crack defect, heat is generated at the defect part due to friction, so that the temperature of the defect part and adjacent areas is obviously increased. When the defect is positioned on the surface or the near surface of the detected component, the change of the surface temperature field can be observed and recorded by using an infrared thermal imager, a time sequence thermal wave signal of the surface of the component is processed by using a computer, and an infrared thermal image of the surface of the component is preliminarily obtained, so that the crack distribution is roughly represented. And then, extracting a characteristic signal of the thermal image by combining a neural network algorithm technology, and further quantitatively predicting the size of the crack.
Compared with the traditional ultrasonic thermal imaging method, the thermal imaging under the laser ultrasonic excitation adopted by the invention can realize non-contact detection of defects, and has good adaptability to severe detection environments such as high temperature and high pressure. In addition, the pulse laser irradiates the surface of the component, the generated ultrasonic wave directly propagates to the crack area, the ultrasonic energy loss is small, and the laser also generates the heat effect, so the heat change at the crack is particularly obvious.
For a metal additive manufacturing component with micro cracks on the surface or the near surface, the position, the width and even the depth of the micro cracks on the surface of the component can be accurately detected by utilizing two technologies of laser ultrasonic and thermal imaging. Based on the method, the defect cracks in the product can be effectively found, so that the cracks are prevented from finally expanding into cracks, and the occurrence of fracture accidents is prevented.
As shown in fig. 3, the present invention provides a non-destructive inspection system for an additive manufactured component, comprising: the device comprises a pulse laser 1, a thermal infrared imager 2, a laser light path unit 3, a thermal signal transmission cable 4, a computer 5, a collecting head motion control mechanism 6, an infrared camera 7, a laser head 8 and an objective table 10.
The additive manufacturing component 9 is arranged below or laterally below the laser head 8, and the laser head 8 is used for applying laser energy to the surface of the additive manufacturing component 9 and generating ultrasonic waves on the surface, so that vibration friction of a defect part of the additive manufacturing component 9 is caused, heat is generated, and the temperature distribution of the surface of an object is different. Because the invention adopts a laser ultrasonic mode, compared with a contact detection mode, the additive manufacturing component 9 can be placed below or laterally below the laser head 8, and the placement position is more random.
The infrared camera 7 and the thermal infrared imager 2 are placed around the additive manufacturing component 9 to record changes in the surface temperature field of the additive manufacturing component 9 in real time. The thermal infrared imager 2 is connected to the computer 5 and transmits the recorded temperature field of the surface of the additive manufacturing component 9 to the computer 5. The thermal infrared imager 2 can detect the temperature difference between the defect area and the normal area. The thermal infrared imager 2(FLIR A65, resolution 640 multiplied by 512 pixels, detection temperature range of minus 25 ℃ to plus 135 ℃ and spectral band of 7.5 to 13 mu m) records the temperature field of the surface of the component. If the thermal infrared imager 2 is matched with a lens with the diameter of 25mm, the spatial resolution can reach 0.68mrad, and the image frame frequency is 30 Hz.
The computer 5 performs calculation processing on the received thermal wave-time sequence signal, thereby obtaining defect information, such as crack size information, of the surface of the member, and realizing non-contact and non-immersion nondestructive detection and flaw detection on the object to be detected.
The laser head 8 is connected to the pulse laser 1, the pulse laser 1 is used for adjusting parameters such as power, action time and the like of a laser emitting device in real time, and parameters such as acting force, ultrasonic action time and amplitude of ultrasonic waves are indirectly adjusted by adjusting the pulse laser 1. The pulsed laser 1 is also connected to the computer 5.
During operation, pulse laser 1 control laser head 8 sends the laser beam, laser head 8 acts on the laser beam additive manufacturing component 9, and the surface produces the ultrasonic wave, causes the vibration friction of additive manufacturing component 9 defective portion, produces the heat, causes the temperature difference of component defect and surrounding area, and the temperature image of this object by thermal infrared imager 2 records and transmits to computer 5 form the surface temperature field image on the computer 5.
In particular, the infrared camera 7 and the laser head 8 may be connected together and manipulated by the pick head motion control mechanism 6 via a robotic arm to effect scanning of different areas of the surface of the additive manufactured component 9 to obtain infrared thermal images at different excitation locations. The thermal infrared imager 2 inputs the temperature change information into the computer 5, and the next step trains thermal infrared imaging data by combining a long-time memory neural network LSTM calculation method to obtain a mapping relation between a temperature signal and crack size information.
Fig. 1 shows a flow chart of the thermal imaging signal processing under laser ultrasonic excitation. The data processing process can be divided into two parts, wherein the first part is crack position determination and temperature characteristic extraction, and the second part is long-time memory neural network LSTM training.
And determining the position of the crack through a thermal image of the surface of the component transmitted by the thermal infrared imager, extracting the temperature of the crack and the characteristic value of the temperature gradient, and training by taking the characteristic values as input values of a neural network. It is noted that in order to improve the detection accuracy of the crack size, the number of samples participating in training needs to be increased, i.e. as many samples as possible are collected.
Taking prediction or identification of crack size as an example, the method for quantitatively predicting the surface cracks of the additive manufacturing component by using an infrared thermal imaging detection system under laser ultrasonic excitation comprises the following specific steps:
1. placing the detected additive manufacturing component 9 below or laterally below the laser head 8, and adjusting parameters (laser energy, laser wavelength, pulse width and the like) of the pulse laser 1 to enable the component defect temperature to reach a temperature range required by the thermal infrared imager 2;
2. the laser head 8 receives the control signal of the pulse laser 1 and then emits laser to the additive manufacturing component 9; the laser acts on the surface of the additive manufacturing component 9 to generate ultrasonic waves;
3. when ultrasonic waves propagate in the additive manufacturing component 9, vibration friction is caused at a defect part inside the additive manufacturing component 9, heat energy is generated, and selective thermal excitation on the defect part is achieved. Transferring heat energy generated at the defect to the surface of the additive manufacturing component 9 through thermal diffusion to generate local temperature change of the surface, and continuously observing and recording the temperature field change of the surface of the additive manufacturing component 9 through the thermal infrared imager 2;
4. the infrared camera 7 and the laser head 8 are fixed together through a mechanical arm, and are controlled by the collecting head motion control mechanism 6, so that the surface of the whole component is scanned, and the computer 5 is used for processing and analyzing heat map data from the thermal infrared imager 2 at different excitation positions to acquire a heat map sequence of the detected surface temperature field of the additive manufacturing component 9;
5. analyzing the infrared image through the computer 5 to obtain the crack position of the surface of the component, extracting the temperature characteristic of the crack, and taking the extracted characteristic value as an input signal for long-time memory neural network LSTM training;
6. and (4) using the temperature characteristic values at different excitation positions for training the neural network, and finally predicting the size of the crack.
The nondestructive testing method and system for the additive manufacturing component provided by the embodiment of the invention at least have the following technical effects:
the invention adopts a non-contact and nondestructive excitation mode capable of controlling and adjusting, and the placement position of the detected additive manufacturing component is more flexible; the heat source excitation mode is laser ultrasonic excitation, and thermal imaging in the excitation mode can realize non-contact detection of component defects, and has good adaptability to severe detection environments such as high temperature and high pressure. The pulse laser irradiates the surface of the component, the generated ultrasonic wave is directly transmitted to the defect area, the ultrasonic energy loss is small, and the laser can also generate a heat effect, so that the heat change at the defect position is particularly obvious, and the method is suitable for defect detection of materials which are irregular in shape, are not easy to contact and the like. In addition, the invention quantitatively predicts the specific width and even depth of the micro defect by using a neural network training method, and provides a practical basis for ensuring that the product meets the engineering index.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to examples, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818533.0A CN113624804A (en) | 2021-07-20 | 2021-07-20 | Nondestructive testing method and system for additive manufacturing component |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818533.0A CN113624804A (en) | 2021-07-20 | 2021-07-20 | Nondestructive testing method and system for additive manufacturing component |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113624804A true CN113624804A (en) | 2021-11-09 |
Family
ID=78380311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110818533.0A Pending CN113624804A (en) | 2021-07-20 | 2021-07-20 | Nondestructive testing method and system for additive manufacturing component |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113624804A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114674874A (en) * | 2022-03-10 | 2022-06-28 | 湖北中桥科技有限公司 | Method and system for detecting slurry filling in prestressed pipeline based on infrared thermal imaging |
| CN114878777A (en) * | 2022-07-12 | 2022-08-09 | 北京煜鼎增材制造研究院有限公司 | High-throughput preparation and characterization system and method for high-temperature alloy based on additive manufacturing |
| CN115015270A (en) * | 2022-05-25 | 2022-09-06 | 中国民航大学 | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared |
| CN115356400A (en) * | 2022-08-11 | 2022-11-18 | 苏州大学 | A method and system for ultrasonic wood non-destructive testing based on BiLSTM |
| CN116363045A (en) * | 2021-12-28 | 2023-06-30 | 哈尔滨工业大学 | A system for intelligent perception and retroactive repair of defects in additive-subtractive composite manufacturing process and its control method |
| CN117571712A (en) * | 2023-08-17 | 2024-02-20 | 哈尔滨工业大学 | A mixed-frequency laser-induced ultrasonic infrared multi-field imaging detection device and method for reusing multiple types of cross-scale damage on spacecraft |
| CN118641627A (en) * | 2024-06-11 | 2024-09-13 | 合肥工业大学 | A stamping sheet metal defect detection system and method based on infrared imaging |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101713756A (en) * | 2009-12-24 | 2010-05-26 | 首都师范大学 | Non-contact ultrasonic thermal-excitation infrared imaging nondestructive detection method and system |
| CN102033081A (en) * | 2010-10-15 | 2011-04-27 | 哈尔滨工业大学 | Infrared lock-in thermal wave non-destructive detection method based on image sequence processing |
| CN111151751A (en) * | 2020-01-02 | 2020-05-15 | 汕头大学 | Three-laser-beam intelligent material-increasing and material-decreasing composite manufacturing system and method |
-
2021
- 2021-07-20 CN CN202110818533.0A patent/CN113624804A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101713756A (en) * | 2009-12-24 | 2010-05-26 | 首都师范大学 | Non-contact ultrasonic thermal-excitation infrared imaging nondestructive detection method and system |
| CN102033081A (en) * | 2010-10-15 | 2011-04-27 | 哈尔滨工业大学 | Infrared lock-in thermal wave non-destructive detection method based on image sequence processing |
| CN111151751A (en) * | 2020-01-02 | 2020-05-15 | 汕头大学 | Three-laser-beam intelligent material-increasing and material-decreasing composite manufacturing system and method |
Non-Patent Citations (5)
| Title |
|---|
| WENXIONG SHI等: ""A technique combining laser spot thermography and neural network for surface crack detection in laser engineered net shaping"", 《OPTICS AND LASERS IN ENGINEERING》 * |
| 刘松平;郭恩明;刘菲菲;李乐刚;杜丽婷;: "激光超声检测碳纤维增强树脂基复合材料的缺陷评估技术研究" * |
| 张立东,李方贵: "激光超声技术在NDT中的应用" * |
| 李圣贤;朱永凯;王海涛;徐成志;: "复合材料分层缺陷的激光超声检测" * |
| 胡婷萍;高丽敏;杨海楠;: "激光超声技术在航空复合材料无损检测中的应用" * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116363045A (en) * | 2021-12-28 | 2023-06-30 | 哈尔滨工业大学 | A system for intelligent perception and retroactive repair of defects in additive-subtractive composite manufacturing process and its control method |
| CN114674874A (en) * | 2022-03-10 | 2022-06-28 | 湖北中桥科技有限公司 | Method and system for detecting slurry filling in prestressed pipeline based on infrared thermal imaging |
| CN115015270A (en) * | 2022-05-25 | 2022-09-06 | 中国民航大学 | Near-surface defect on-wing detection method for aero-engine component based on hot air infrared |
| CN114878777A (en) * | 2022-07-12 | 2022-08-09 | 北京煜鼎增材制造研究院有限公司 | High-throughput preparation and characterization system and method for high-temperature alloy based on additive manufacturing |
| CN114878777B (en) * | 2022-07-12 | 2022-10-14 | 北京煜鼎增材制造研究院有限公司 | High-throughput preparation and characterization system and method for high-temperature alloy based on additive manufacturing |
| CN115356400A (en) * | 2022-08-11 | 2022-11-18 | 苏州大学 | A method and system for ultrasonic wood non-destructive testing based on BiLSTM |
| CN117571712A (en) * | 2023-08-17 | 2024-02-20 | 哈尔滨工业大学 | A mixed-frequency laser-induced ultrasonic infrared multi-field imaging detection device and method for reusing multiple types of cross-scale damage on spacecraft |
| CN118641627A (en) * | 2024-06-11 | 2024-09-13 | 合肥工业大学 | A stamping sheet metal defect detection system and method based on infrared imaging |
| CN118641627B (en) * | 2024-06-11 | 2025-01-28 | 合肥工业大学 | A stamping sheet metal defect detection system and method based on infrared imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113624804A (en) | Nondestructive testing method and system for additive manufacturing component | |
| US11633918B2 (en) | Method and device for additive manufacturing utilizing simulation test results of a workpiece | |
| US7605924B2 (en) | Laser-ultrasound inspection using infrared thermography | |
| JP5307155B2 (en) | Nondestructive inspection using laser ultrasound and infrared thermography | |
| CN102866144B (en) | Nondestructive testing method for fatigue crack on solid material surface | |
| CN111175233A (en) | Laser ultrasonic detection method and system for laser precision spot welding quality | |
| CN107462599B (en) | Microwave thermoacoustic detection monitoring system and method | |
| CN109211974B (en) | Pulse femtosecond laser infrared thermal wave detection device and method for debonding defect of thermal barrier coating | |
| CN110763764A (en) | A New Ultrasonic Detection System for Metal Internal Defects | |
| US12169397B2 (en) | Method, system and device for acquisition and processing of elastic waves and field sensor data for real-time in-situ monitoring of additive manufacturing | |
| CN211179651U (en) | A New Ultrasonic Detection System for Metal Internal Defects | |
| JP2020518827A (en) | Laser thermography | |
| CN110687204A (en) | Method and device for laser ultrasonic testing | |
| Davis et al. | Near-surface defect detection in additively manufactured components using laser induced phased arrays with surface acoustic wave crosstalk suppression | |
| CN109799191B (en) | Optical non-contact detection device and method for acoustic disturbance on rough surface of solid material | |
| CN113504182A (en) | Object surface crack online detection method based on laser surface acoustic wave | |
| CN113155967A (en) | Phased array nonlinear laser ultrasonic detection system | |
| Long et al. | Large-field detection of Metal/CFRP hybrid composites based on air-coupled laser ultrasound | |
| JP2006170684A (en) | Inspection method and inspection device for press failure | |
| CN113358753A (en) | Laser cladding crack online identification device and positioning method based on acoustic characteristics | |
| CN115684351B (en) | Ultrasonic quantitative evaluation device and method for impact damage of carbon fiber composite material | |
| Sohn et al. | Non-contact laser ultrasonics for SHM in aerospace structures | |
| JP4595117B2 (en) | Ultrasound propagation imaging method and apparatus | |
| CN115389620A (en) | Laser ultrasonic nondestructive testing device and method for high-temperature load in-situ detection | |
| Cramer et al. | Quantitative NDE of Composite Structures at NASA |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211109 |
|
| RJ01 | Rejection of invention patent application after publication |