Metal component defect type detection method

Abstract

The invention provides a metal component defect type detection method which comprises the following steps: preparing metal component defect samples and metal component defect-free samples with different defect types to construct a sample set; transmitting pulse laser to a plurality of specific positions of each sample, and simultaneously collecting a plasma image and an LIBS spectrum of the sample; for a plasma image and an LIBS spectrum collected at the same specific position of the sample, respectively extracting plasma image features and LIBS spectrum features to obtain fusion features at each specific position of the sample and a fusion feature trend of the sample; based on the fusion feature trend and the defect type of each sample, constructing a defect identification model by using a linear discriminant analysis method; and acquiring plasma images and LIBS spectrums at a plurality of target positions of the to-be-detected metal component to obtain a fusion feature trend, and detecting defect types by using the defect identification model. According to the method, the detection performance of defect types can be improved by combining plasma image features.

Description

Technical Field

[0001] The present application belongs to the technical field of metal component defect detection, and in particular, relates to a method for detecting defect types of metal components. Background Art

[0002] Metal additive manufacturing (AM) technology has been widely used in aerospace, automobile manufacturing and other industries in recent years. However, due to its complex processing process, AM components often have defects such as pores, cracks, and protrusions, which may affect the performance and reliability of the components. Therefore, the detection technology for AM component defects has become a hot topic in current research.

[0003] Laser induced breakdown spectroscopy (LIBS) technology is a high-precision, high-sensitivity optical analysis method that is widely used for rapid detection of element types and concentrations. With the in-depth study of the relationship between LIBS spectral characteristics and element types, the application of this technology has expanded from traditional component analysis to more complex fields, such as circuit aging prediction, battery evaluation, and material performance monitoring. Especially in the field of metal AM, LIBS technology has shown great potential in defect detection due to its significant advantages of no sample preparation, rapid in-situ detection, and high spatial resolution. Therefore, many domestic and foreign researchers have applied LIBS to defect identification and quality control of metal AM components.

[0004] In the study of spatial effects of LIBS, domestic and foreign scholars mainly focus on enhancing the signal intensity of plasma and improving experimental repeatability through different spatial constraint structures and sizes. For cylindrical cavities, a dual enhancement mechanism of N2 atmosphere and cylindrical cavity confinement is proposed to improve the detection performance of LIBS for Sr elements in soil. Under the optimal conditions (cavity diameter 2mm, height 6mm), the enhancement factor is 3.2. For hemispherical cavities, the effect of laser energy on the enhancement characteristics of hemispherical cavity confined plasma is studied. When the laser energy exceeds 80mJ, the plasma under the hemispherical cavity confinement is significantly enhanced within 8-14μs, and the enhancement factor increases with the increase of laser energy. For parallel wall cavities, by synchronously acquiring plume and shock wave images, it is found that the reflected shock wave under parallel cavity confinement compresses the plasma, significantly enhancing the emission intensity and improving the signal reproducibility, and this effect only appears within a specific time window.

[0005] Most of the above studies are based on the fact that the ablation point of LIBS acts on the center of a symmetrical structure (cylindrical cavity, hemispherical cavity, parallel wall cavity, etc.), forming a symmetrical spatial effect, so that the reflected shock wave can uniformly compress the plasma. However, in actual metal AM components, defects often present asymmetric structures, which leads to asymmetric characteristics of the spatial effect caused by the defects. At present, there are no reports on the interaction mechanism of asymmetric spatial effects on LIBS plasma. Summary of the invention

[0006] In view of this, the purpose of the present application is to provide a method for detecting defect types of metal components. By combining plasma image features and LIBS spectral features, the detection performance of defect types can be improved, especially based on the asymmetric spatial effect shown by crack defects, crack defects and pit defects can be fully distinguished.

[0007] The present application provides a method for detecting defect types of metal components, the method comprising: Preparing defective samples of metal components with different defect types and non-defective samples of metal components to construct a sample set; wherein the defect types include: cracks, potholes and bulges; For each sample, a pulsed laser is emitted to multiple specific positions of the sample, and the plasma image and LIBS spectrum of the sample are collected simultaneously; For the plasma image and LIBS spectrum collected at the same specific position of the sample, the plasma image features and the LIBS spectrum features are extracted respectively to obtain the fusion features at each specific position of the sample; Based on the fusion features at each specific position of the sample, a fusion feature trend of the sample is obtained; Based on the fusion feature trends and defect types of each sample, a defect recognition model is constructed using linear discriminant analysis; The plasma images and LIBS spectra at multiple target positions of the metal component to be detected are collected to obtain the fusion feature trend of the metal component to be detected, and the defect type of the metal component to be detected is detected using the defect recognition model.

[0008] Furthermore, when the sample is a metal component defect sample, emitting pulsed lasers at multiple specific positions of the sample and simultaneously collecting a plasma image and a LIBS spectrum of the sample include: Determine the defect location of the sample and identify the defect edge; Taking any edge of the defect as a starting point and the approximate center position of the defect as an end point, multiple specific positions are selected at specific length intervals; wherein the specific positions do not include the defect edge; For each specific position, a pulsed laser is emitted for ablation, and the plasma image and LIBS spectrum of the sample at the specific position are collected simultaneously.

[0009] Furthermore, when the sample is a defect-free sample of a metal component, emitting a pulsed laser to a plurality of specific positions of the sample for ablation, and simultaneously collecting a plasma image and a LIBS spectrum of the sample, comprises: A plurality of specific locations are randomly selected on the surface of the sample; For each specific position, a pulsed laser is emitted for ablation, and the plasma image and LIBS spectrum of the sample at the specific position are collected simultaneously.

[0010] Furthermore, before respectively extracting the plasma image features and the LIBS spectrum features to obtain the fusion features at each specific position of the sample, the method further includes: For each plasma image, the plasma image is divided into different regions using an edge detection algorithm to obtain plasma image features; For each LIBS spectrum, the principal component analysis method is used to extract the principal component that can reflect the spectral characteristics to obtain the LIBS spectral characteristics.

[0011] Furthermore, the plasma image is divided into different regions using an edge detection algorithm to obtain plasma image features, including: The plasma image is divided into inner, middle and outer regions from the inside to the outside by using an edge detection method; The dividing line between the inner and middle regions is defined as the middle-inner layer, and the dividing line between the middle and outer regions is defined as the middle-outer layer; By using image processing technology, the contour length and the inner area of ​​the middle inner layer and the middle outer layer are extracted as key size features; The key size features are used to calculate the near-circularity of the middle inner layer and the middle outer layer, as well as the proportion of the middle and outer regions in the plasma image, so as to obtain the plasma image features.

[0012] Furthermore, the principal component analysis method is used to extract the principal component that can reflect the spectral characteristics to obtain the LIBS spectral characteristics, including: Preprocessing of LIBS spectra for background subtraction and normalization; Based on the preprocessed LIBS spectra, multiple principal components that can explain the LIBS spectral characteristics are extracted, and the explained variance of each principal component is calculated; According to the cumulative proportion of explained variance, a specific number of principal components with high rankings were selected to construct LIBS spectral features.

[0013] Furthermore, the collecting of plasma images and LIBS spectra at multiple target positions of the metal component to be detected to obtain the fusion feature trend of the metal component to be detected includes: Extracting plasma image features and LIBS spectrum features at multiple target positions of the metal component to be detected to obtain fusion features at multiple target positions of the metal component to be detected; Based on the fusion features at multiple target positions of the metal component to be detected, a fusion feature trend of the metal component to be detected is obtained.

[0014] The metal component defect type detection method provided in the present application can improve the detection performance of defect types by combining plasma image features and LIBS spectral features, especially based on the asymmetric spatial effect exhibited by crack defects, it can fully distinguish between crack defects and pit defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a parallel wall cavity sample provided in an embodiment of the present application is shown; Figure 2 The device for collecting plasma images and LIBS spectra provided in the embodiments of the present application is shown; Figure 3 The following is a graph showing the evolution trend of spectral intensity over time under unconstrained conditions provided by an embodiment of the present application; Figure 4 A schematic diagram of the plasma evolution process of the asymmetric spatial effect provided by an embodiment of the present application is shown; Figure 5 The variation trend diagram of the spectral intensity, delay time and enhancement factor under the reflected shock waves of the left and right side walls of the parallel cavity provided by the embodiment of the present application is shown; Figure 6 The evolution images of plasma morphology under asymmetric spatial confinement (DAPLW = 1mm-7mm) and without spatial confinement provided by the embodiments of the present application are shown; Figure 7 A flow chart of a method for detecting metal component defect types provided in an embodiment of the present application is shown; Figure 8 An example diagram showing a defective sample of a metal component and a non-defective sample of a metal component provided in an embodiment of the present application is shown; Fig. 9 A regional division model diagram of a plasma image provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the technical solution more clear, the technical solution is further described in detail below in conjunction with specific implementation methods. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the technical solution.

[0017] Embodiment 1

[0018] The first embodiment of the present application explores the influence of asymmetric spatial effect on the morphology and spectral characteristics of LIBS plasma. Firstly, a chromium-iron alloy material is used to prepare a planar sample and a Figure 1 The parallel wall cavity sample shown is used to simulate crack defects in metal components, where Figure 1 (a), (b), and (c) are the three-dimensional image, top view, and front view of the parallel wall cavity sample, respectively. Figure 1 As shown, the size of the outer surface of the parallel wall cavity is 24mm×15mm×5mm, and the width and height of the inner surface of the parallel wall cavity are 14mm and 3mm respectively. Here, the types of defects that affect the quality of metal components mainly include: cracks, pits and convex defects, among which convex defects are relatively easy to identify, and cracks and pits are difficult to distinguish because they both present a concave surface. Then, clarifying the spectral characteristics and plasma behavior characteristics of one of the defects means distinguishing between the two defects. Therefore, in the first embodiment of the present application, the crack defect with more obvious spectral characteristics and plasma behavior characteristics is taken as the research object, and further, the parallel wall cavity similar to the crack defect is taken as the experimental model.

[0019] Secondly, build Figure 2 The plasma image and LIBS spectrum acquisition device shown. A Q-switched Nd:YAG laser (Vlite-200 model, wavelength 1064nm, energy 60mJ, pulse width 8ns, repetition rate 1Hz, beam mode TEM00) was used as the ablation source. The pulsed laser was reflected by the mirror and lens and focused 2mm below the sample surface, inducing plasma. The optical signal emitted by the plasma was collected by the optical fiber probe, and the signal was transmitted to the spectrometer (SR-500i-a, Andor), and then the ICCD detector (1024×1024 pixels, Andor) converted the optical signal into digital information and stored in the computer. The spectral wavelength acquisition range is 250nm~650nm, with a resolution of 0.07nm. The gate width was set to 1µs and the delay step was 1µs to measure the emission time characteristics of the plasma during the acquisition delay of 1µs to 22µs. At the same time, the plasma image is recorded by a high-speed camera (model Dicam-pro, zoom range 24-85mm, aperture range f / 22 to f / 2.8, resolution 1280x1024, frame rate 8fps, pixel size 6.7µm), and the image data is saved in a computer for subsequent analysis. The acquisition process of LIBS spectral information and plasma image information is synchronous, and the timing of all laser emission, plasma information acquisition and other behaviors is controlled by a multifunctional digital delay pulse generator (model BNC-575).

[0020] Then, for the planar sample, the pulse laser is directly irradiated on the sample surface. For the parallel wall cavity sample, the distance between the ablation point and the left parallel wall is defined as DAPLW, and DAPLW is set to 1mm, 2mm, 3mm, 4mm, 5mm, 6mm, and 7mm (located in the middle of the groove), where 7mm is the symmetrical position and the rest are asymmetrical positions.

[0021] Finally, the spectral characteristics analysis and plasma behavior analysis are performed on the collected LIBS spectra and plasma images.

[0022] (1) Select the characteristic spectral lines of LIBS spectrum: The spectral lines selected in the first embodiment of the present application should meet the following principles: they must be effectively acquired in the late plasma stage to ensure the stability and reliability of the data in the actual measurement process; they should be less interfered by other elements, so as to reduce the influence of cross-interference on the spectral line intensity, thereby improving the accuracy of the analysis. Figure 3 The evolution trend of spectral intensity over time under unconstrained conditions is shown in the figure, where Figure 3 (a) is the overall evolution trend of the delay time in the range of 1-22µs. Figure 3 (b) is a spectrum diagram when the delay time is 22µs. As shown in the figure, according to the above two principles, three spectrum lines Cr I 425.43nm, Mn II 463.92nm and Fe I 519.87nm are finally determined as the characteristic spectrum lines of Example 1 of the present application.

[0023] (2) Theoretical analysis: When the laser-induced plasma expands in the air, the plasma from the ablation target will generate a shock wave, which will affect the entire LIBS process. Specifically, based on the spatial confinement effect, the increase in plasma temperature and density is caused by the reflection of the shock wave from the cavity wall. When the shock wave reaches the inner surface of the confinement cavity and reflects back, it continues to propagate toward the plasma, interacts with the plasma, and enhances inter-particle collisions, thereby increasing the plasma temperature and density. At the same time, the shock wave heating effect also enhances the emission intensity of the plasma, thereby increasing the intensity of the spectral lines. For the plasma evolution process of the asymmetric spatial effect, the ablation point is located at an asymmetric position, and the following is drawn. Figure 4 Schematic diagram of plasma evolution due to asymmetric spatial effects. When plasma is induced at an asymmetric position (left of the center line), the generation of plasma is accompanied by the outward diffusion of the front shock wave (see Figure 4 (a)); This diffuse shock wave is reflected when it encounters the relatively close left wall, forming a left wall reflected shock wave (see Figure 4 (b)); The left wall reflected shock wave first acts on the plasma, causing changes in its spectral characteristics and morphology (see Figure 4 (c)); Subsequently, the plasma is affected by the shock wave reflected from the right wall, which causes more complex changes (see Figure 4 (d)).

[0024] (3) Analysis of spectral characteristics: The first embodiment of the present application conducts quantitative analysis on the following parameters: spectral intensity, enhancement factor, and corresponding delay time to explore the spectral characteristics of defective samples. Among them, spectral intensity is the most intuitive spectral characteristic parameter, which can provide direct information about the plasma state; the enhancement factor quantifies the degree of improvement of spectral intensity relative to the unconstrained spectral emission signal under the asymmetric spatial effect, reflecting the influence of different DAPLW on plasma characteristics; the corresponding delay time is used to describe the response time of the excitation signal corresponding to the enhancement factor.

[0025] Explore the impact of asymmetric spatial effects on spectral properties: see e.g. Figure 5 The variation trend of spectral intensity, delay time and enhancement factor under the reflected shock wave of the left and right side walls of the parallel cavity is shown. Among them, asymmetric spatial confinement is generated when DAPLW is 1mm-6mm, and symmetric spatial confinement is generated when DAPLW is 7mm.

[0026] Depend on Figure 5 From the overall variation trend of the spectral intensity shown in (a) and (d), it can be seen that with the increase of DAPLW, the spectral intensity of the characteristic spectral line under the shock wave reflected from the left wall shows a downward trend, while the spectral intensity of the shock wave reflected from the right wall shows an upward trend. Figure 5 From the overall variation trend of the delay time shown in (b) and (e), it can be seen that the initial delay time of the shock wave reflected from the left wall is 2µs (DAPLW=1mm), and the propagation time increases with the increase of DAPLW; while the initial delay time of the shock wave reflected from the right wall is 16µs (DAPLW=3mm). This is because when DAPLW=1 and 2mm, the shock wave energy of the shock wave reflected from the right wall is weak when it acts on the plasma, and the enhancement effect is not obvious, and the propagation time decreases with the increase of DAPLW; finally, the synchronous action time of the reflected shock waves on the left and right sides is 10µs (DAPLW=7mm). Figure 5 From the overall variation trend of the enhancement factors shown in (c) and (f), it can be seen that all enhancement factors are greater than 1, indicating that the reflected shock waves on the left and right sides have an enhancement effect on the characteristic spectral lines. As DAPLW increases from 2 mm to 7 mm, the enhancement effect of the reflected shock waves on the left wall gradually decreases and reaches the lowest point when DAPLW=6 mm. When DAPLW=7 mm, it rebounds due to the influence of the reflected shock waves on the right wall. In contrast, the enhancement effect of the reflected shock waves on the right wall on the spectral lines shows a gradually increasing trend.

[0027] The above phenomenon shows that when DAPLW changes from 1 to 6 mm, there is a significant difference in the impact of the reflected shock waves from the left and right side walls on the spectrum, that is, an asymmetric spatial effect is presented. It should be noted that when DAPLW = 7 mm, the reflected shock waves from the left and right side walls act on the plasma synchronously. At this time, the symmetric spatial confinement effect emerges, and the enhancement factors of the characteristic spectral lines reach 4.5, 4.71, and 3.73, respectively. This shows that under the symmetric spatial effect, the enhancement effect of the spectral line intensity is better than that of the asymmetric spatial effect. Specifically, the asymmetric spatial effect will cause the plasma to not be uniformly compressed, resulting in partial energy loss, which in turn affects the spectral line intensity. Under the symmetric spatial effect, the plasma can be compressed more uniformly, and the spectral intensity is more effectively enhanced.

[0028] (4) Analysis of plasma behavior characteristics: Please refer to Figure 6 The evolution of plasma morphology under asymmetric spatial confinement (DAPLW = 1mm-7mm) and without spatial confinement is shown. The first image for all conditions was taken with a time delay of 1µs, and the time delay of each subsequent image was increased by 1µs. Figure 6 It can be seen that the evolution of plasma morphology can be roughly divided into four stages: Phase 1 (1µs): The plasma is relatively small but has a higher temperature and electron density, resulting in a larger spectral intensity.

[0029] Stage 2 (2µs- 10µs): The plasma morphology is relatively stable. In particular, when DAPLW = 1mm, the plasma shows a tendency to tilt to the right, while there is no significant tilt change under other conditions. This is because when DAPLW = 1mm, the ablation point is close to the left wall, and the reflected shock wave energy compresses the plasma, causing the plasma to be subjected to an external force toward the right wall, resulting in a tendency to deviate to the right. As DAPLW increases, the energy of the shock wave reflected by the left wall gradually weakens, and the tendency of the plasma to deviate to the right also gradually decreases. When DAPLW = 2mm-7mm, there is no obvious tilt change in the plasma morphology.

[0030] Stage 3 (10µs ~ 13µs): The plasma morphology under all conditions changes significantly, which is due to the change in the particle density core of the plasma. At this time, the plasma evolution trend of DAPLW = 1mm-7mm is similar to the natural evolution trend under the condition of no spatial confinement.

[0031] Stage 4 (13µs ~ 22µs): As time goes by, the temperature and electron density of the plasma gradually decrease, and the morphology is more susceptible to interference from external factors. For example, under the condition of DAPLW = 3mm, when the delay time is 15µs, the plasma morphology is affected by the shock wave compression reflected by the right wall and the shock wave energy brought in, causing the morphology to be distorted, thereby affecting the temperature and density of the plasma and causing changes in the spectral intensity. Similar phenomena also occur under the conditions of DAPLW = 4mm-6mm. Under the conditions of DAPLW = 1mm and 2mm, although the plasma morphology also undergoes similar changes, it is not reflected in the spectral characteristics. This may be because the shock wave energy reflected by the right-side reflecting wall is low. Although it affects the plasma morphology, it is not enough to cause significant changes in temperature and density.

[0032] By comparing the changes in plasma morphology under different conditions, the following conclusions are drawn: the plasma morphology under the conditions of no spatial constraint and symmetric spatial constraint (DAPLW = 7mm) is relatively stable. The reason is that under the condition of no spatial constraint, the plasma is not disturbed by external forces, and under the action of symmetric spatial constraint, the reflected shock wave uniformly compresses the plasma, resulting in less change in plasma morphology. In other words, the evolution of plasma is significantly affected by asymmetric spatial constraints, especially at smaller DAPLW values, where the effect of reflected shock waves significantly changes the morphology and spectral characteristics of the plasma.

[0033] The evolution of plasma morphology can reflect the microstructure or morphological changes on the surface of the material. In the defect area, the formation and evolution of plasma may show different characteristics from normal areas, such as irregular morphology and uneven expansion. By monitoring the evolution trend of plasma morphology, especially the local irregular changes caused by defects, LIBS technology can be assisted in the effective detection of defects. Furthermore, the plasma morphology evolution process can be characterized by the near circularity of the plasma.

[0034] In summary, compared with the symmetric spatial effect and the behavior of the unconfined case, the plasma under asymmetric spatial confinement exhibits different behavioral characteristics. This discovery is of great significance for the application of LIBS technology in fields with asymmetric structural characteristics (such as metal defect detection).

[0035] Embodiment 2

[0036] Embodiment 2 of the present application discloses a method for detecting defect types of metal components. Figure 7 The flowchart of the metal component defect type detection method provided in the embodiment of the present application is shown, and the method includes: S101. Prepare defective metal component samples with different defect types and non-defective metal component samples to construct a sample set.

[0037] The defect types include: cracks, holes and protrusions.

[0038] In this step, the number of crack, pit, and convex defect samples and non-defect samples prepared is the same. Here, in order to facilitate measurement and modeling, the sizes of the three defects, namely the width of the crack, the diameter of the pit, and the diameter of the convex can be controlled to be uniform. As an example, the size can be set to about 2 mm. Figure 8 Example pictures of defective metal component samples and non-defective metal component samples are shown.

[0039] S102 . For each sample, emit a pulsed laser to multiple specific positions of the sample, and simultaneously collect a plasma image and a LIBS spectrum of the sample.

[0040] In this step, a pulsed laser is fired at a specific location of the sample for ablation to excite plasma, thereby using Figure 2 The plasma image and LIBS spectrum acquisition device shown simultaneously acquires the plasma image and LIBS spectrum of the sample.

[0041] In addition, according to the changing trend of the spectral characteristics and plasma behavior characteristics with the delay time described in Example 1, Example 2 of the present application sets the delay time to 2µs to avoid the delay time from having a significant impact on the spectral characteristics and plasma behavior characteristics at different specific positions, thereby taking the asymmetric spatial effect as the main influencing factor causing changes in spectral intensity and plasma morphology, and at the same time, by setting different collection positions, plasma images and LIBS spectra under different asymmetric spatial effects are obtained.

[0042] Specifically, when the sample is a metal component defect sample, emitting pulsed lasers at multiple specific positions of the sample and simultaneously collecting a plasma image and a LIBS spectrum of the sample include: Step 1021: determine the defect location of the sample and identify the defect edge.

[0043] Step 1022: Taking any edge of the defect as a starting point and the approximate center position of the defect as an end point, multiple specific positions are selected at specific length intervals.

[0044] Wherein, the specific position does not include a defect edge.

[0045] In this step, the length interval can be set according to the size of the defect to determine multiple specific positions, so as to prepare for obtaining plasma images and LIBS spectra under multiple different asymmetric spatial effects. As an example, the length interval of Example 2 of the present application can be set to 250µm. Further, 4 specific positions can be determined, and the distances between the specific positions and the edge of the defect are 250µm, 500µm, 750µm and 1mm respectively. It should be noted that the specific position should be selected inside the defect rather than at the edge of the defect. In addition, for crack defect samples, specific positions need to be set along the width direction of the crack.

[0046] Step 1023: For each specific position, emit a pulsed laser for ablation, and simultaneously collect the plasma image and LIBS spectrum of the sample at the specific position.

[0047] When the sample is a defect-free metal component sample, emitting pulsed lasers at multiple specific positions of the sample for ablation, and simultaneously collecting a plasma image and a LIBS spectrum of the sample, comprises: Step 1024: randomly select a plurality of specific locations on the surface of the sample.

[0048] In this step, in order to maintain data consistency, the length intervals of the non-defective samples and the defective samples are made consistent, so that the number of specific positions is consistent.

[0049] Step 1025 , emitting a pulsed laser for ablation at each specific position, and simultaneously collecting a plasma image and a LIBS spectrum of the sample at the specific position.

[0050] S103, for the plasma image and LIBS spectrum collected at the same specific position of the sample, respectively extract the plasma image features and the LIBS spectrum features to obtain the fusion features at each specific position of the sample.

[0051] In this step, the plasma image features are used to characterize the plasma behavior features, and the LIBS spectral features are used to characterize the spectral characteristics. Based on the analysis results of the above-mentioned embodiment 1, at the same specific position, the plasma behavior characteristics and spectral characteristics of the sample are consistent. Therefore, fusing the plasma image features and the LIBS spectral features can enhance the feature representation at the specific position, that is, obtain the fused features at the specific position.

[0052] As an example, a plasma image and a LIBS spectrum collected at a specific position with a distance of 250 µm from the edge are obtained, so as to extract the plasma image features and the LIBS spectrum features corresponding to the specific position.

[0053] Before respectively extracting the plasma image features and the LIBS spectrum features to obtain the fusion features at each specific position of the sample, the method further comprises: Step 1031 : For each plasma image, use an edge detection algorithm to divide the plasma image into different regions to obtain plasma image features.

[0054] In specific implementation, the plasma image features can be obtained by the following methods: Step 201: Divide the plasma image from the inside to the outside into inner, middle and outer areas using an edge detection method.

[0055] Step 202: define the boundary line between the inner and middle regions as the middle inner layer, and define the boundary line between the middle and outer regions as the middle outer layer.

[0056] In this step, you can refer to Fig. 9 The regional division model diagram of the plasma image is shown.

[0057] Step 203: using image processing technology, extract the contour length and the inner area of ​​the middle inner layer and the middle outer layer as key size features.

[0058] Step 204 , using the key size features, respectively calculate the near-circularity of the middle inner layer and the middle outer layer, and the proportion of the middle and outer regions in the plasma image, thereby obtaining plasma image features.

[0059] Step 1032: For each LIBS spectrum, a principal component that can reflect the spectral characteristics is extracted using a principal component analysis method to obtain the LIBS spectral characteristics.

[0060] In specific implementation, LIBS spectral characteristics can be obtained by the following methods: Step 301: pre-process the LIBS spectrum by background subtraction and normalization.

[0061] Step 302: Based on the preprocessed LIBS spectrum, a plurality of principal components that can explain the LIBS spectrum characteristics are extracted, and the explained variance of each principal component is calculated.

[0062] Step 303: According to the cumulative proportion of explained variance, a specific number of principal components with high rankings are selected to construct LIBS spectral features.

[0063] As an example, the top three principal components, namely the characteristic spectral lines Cr I 425.43 nm, Mn II 463.92 nm and Fe I 519.87 nm selected in the above embodiment 1, are used as the principal components of the LIBS spectral features to construct the LIBS spectral features.

[0064] S104. Based on the fusion features at each specific position of the sample, obtain the fusion feature trend of the sample.

[0065] In this step, different specific positions correspond to different feature representations, that is, asymmetric spatial effects, or symmetric spatial effects. Based on the different feature representations at each specific position, the changing trend of the fusion feature of the sample with each specific position is obtained. For different defective samples, the changing trend of the fusion feature with each specific position is also different, that is, the fusion feature trend can characterize the defect type of the sample.

[0066] S105. Based on the fusion feature trends and defect types of each sample, a defect recognition model is constructed using linear discriminant analysis.

[0067] In this step, based on the fusion feature trend of each sample, the linear discriminant analysis method is used for classification to obtain the predicted defect type of each sample. Based on the original defect type of each sample, the parameters of the linear discriminant analysis method are adjusted to make the predicted defect type of each sample tend to the original defect type of each sample, thereby obtaining a trained defect recognition model.

[0068] S106, collecting plasma images and LIBS spectra at multiple target positions of the metal component to be detected to obtain a fusion feature trend of the metal component to be detected, and using the defect recognition model to detect the defect type of the metal component to be detected.

[0069] In specific implementation, the fusion feature trend of the metal component to be detected can be obtained by the following method: Step 1061 : extracting plasma image features and LIBS spectrum features at multiple target positions of the metal component to be detected to obtain fusion features at multiple target positions of the metal component to be detected.

[0070] In this step, since the defect type and defect position of the metal component to be inspected are unknown, multiple target positions can be selected on the surface of the metal component to be inspected according to the length interval when selecting a specific position, and a target position sequence is constructed. A plasma image and LIBS spectrum are collected at each target position, and the plasma image features and LIBS spectrum features are extracted to obtain fusion features at multiple target positions.

[0071] Step 1062: Based on the fusion features at multiple target positions of the metal component to be detected, obtain a fusion feature trend of the metal component to be detected.

[0072] In this step, the number of specific positions selected above is taken as the target number, and target positions of the target number that can be overlapped are extracted from the target position sequence. The fusion feature trend is obtained based on the fusion features of the extracted target positions until the target position sequence is traversed.

[0073] The above contents are only preferred embodiments of the present invention. For ordinary technicians in this field, many changes can be made in the specific implementation methods and application scopes based on the ideas of the present technical content. As long as these changes do not deviate from the concept of the present invention, they all fall within the scope of protection of this patent.

Claims

1. A method for detecting defect types of metal components, characterized in that: The method comprises: Preparing defective samples of metal components with different defect types and non-defective samples of metal components to construct a sample set; wherein the defect types include: cracks, potholes and bulges; For each sample, a pulsed laser is emitted to multiple specific positions of the sample, and the plasma image and LIBS spectrum of the sample are collected simultaneously; For the plasma image and LIBS spectrum collected at the same specific position of the sample, the plasma image features and the LIBS spectrum features are extracted respectively to obtain the fusion features at each specific position of the sample; Based on the fusion features at each specific position of the sample, a fusion feature trend of the sample is obtained; Based on the fusion feature trends and defect types of each sample, a defect recognition model is constructed using linear discriminant analysis; The plasma images and LIBS spectra at multiple target positions of the metal component to be detected are collected to obtain the fusion feature trend of the metal component to be detected, and the defect type of the metal component to be detected is detected using the defect recognition model.

2. The method according to claim 1, characterized in that When the sample is a metal component defect sample, emitting pulsed lasers at multiple specific positions of the sample and simultaneously collecting a plasma image and a LIBS spectrum of the sample include: Determine the defect location of the sample and identify the defect edge; Taking any edge of the defect as a starting point and the approximate center position of the defect as an end point, multiple specific positions are selected at specific length intervals; wherein the specific positions do not include the defect edge; For each specific position, a pulsed laser is emitted for ablation, and the plasma image and LIBS spectrum of the sample at the specific position are collected simultaneously.

3. The method according to claim 1, characterized in that When the sample is a defect-free metal component sample, emitting pulsed lasers at multiple specific positions of the sample for ablation, and simultaneously collecting a plasma image and a LIBS spectrum of the sample, comprises: A plurality of specific locations are randomly selected on the surface of the sample; For each specific position, a pulsed laser is emitted for ablation, and the plasma image and LIBS spectrum of the sample at the specific position are collected simultaneously.

4. The method according to claim 1, characterized in that Before respectively extracting the plasma image features and the LIBS spectrum features to obtain the fusion features at each specific position of the sample, the method further comprises: For each plasma image, the plasma image is divided into different regions using an edge detection algorithm to obtain plasma image features; For each LIBS spectrum, the principal component analysis method is used to extract the principal component that can reflect the spectral characteristics to obtain the LIBS spectral characteristics.

5. The method according to claim 4, characterized in that The plasma image is divided into different regions using an edge detection algorithm to obtain plasma image features, including: The plasma image is divided into inner, middle and outer regions from the inside to the outside by using an edge detection method; The dividing line between the inner and middle regions is defined as the middle-inner layer, and the dividing line between the middle and outer regions is defined as the middle-outer layer; By using image processing technology, the contour length and the inner area of ​​the middle inner layer and the middle outer layer are extracted as key size features; The key size features are used to calculate the near-circularity of the middle inner layer and the middle outer layer, as well as the proportion of the middle and outer regions in the plasma image, so as to obtain the plasma image features.

6. The method according to claim 4, characterized in that The principal component analysis method is used to extract the principal component that can reflect the spectral characteristics to obtain the LIBS spectral characteristics, including: Preprocessing of LIBS spectra for background subtraction and normalization; Based on the preprocessed LIBS spectra, multiple principal components that can explain the LIBS spectral characteristics are extracted, and the explained variance of each principal component is calculated; According to the cumulative proportion of explained variance, a specific number of principal components with high rankings were selected to construct LIBS spectral features.

7. The method according to claim 1, characterized in that The collecting of plasma images and LIBS spectra at multiple target positions of the metal component to be detected to obtain a fusion feature trend of the metal component to be detected includes: Extracting plasma image features and LIBS spectrum features at multiple target positions of the metal component to be detected to obtain fusion features at multiple target positions of the metal component to be detected; Based on the fusion features at multiple target positions of the metal component to be detected, a fusion feature trend of the metal component to be detected is obtained.

Images