A component multi-dimensional information measurement method and system based on multi-source information fusion

Abstract

A kind of component multidimensional information measurement method and system based on multi-source information fusion, method includes:1, obtain the fluorescent speckle image before deformation, texture image, two images are all decomposed into low-frequency feature, high-frequency feature by discrete wavelet transform;2, the low-frequency feature of fluorescent speckle image before deformation, texture image is fused;The high-frequency feature of fluorescent speckle image before deformation, texture image is fused;3, the low-frequency feature, high-frequency feature after fusion is reconstructed by inverse wavelet transform to obtain the fusion image before deformation;4, obtain the fusion image after deformation;5, obtain the three-dimensional topography of component using FPP method;Then calculate subpixel level displacement field, and construct three-dimensional displacement field according to three-dimensional topography and subpixel level displacement field;Extract the partial derivative of three-dimensional displacement field to pixel coordinates, calculate green strain tensor.The present application effectively overcomes the interference of environmental factors to displacement and strain measurement, improves the measurement accuracy and robustness.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of optical measurement and computer vision, in particular to a component multi-dimensional information measurement method and system based on multi-source information fusion. BACKGROUND

[0002] With the development of intelligent manufacturing and industrial detection technology, the measurement of complex component's morphology, strain and displacement has become one of the key technologies. At present, the commonly used measurement methods include fringe projection profilometry (FPP) and digital image correlation (DIC). Fringe projection profilometry can obtain the surface morphology information of the component with high precision by projecting a fringe pattern and analyzing the reflected image, but it cannot directly provide the displacement and strain information of the component. Digital image correlation is a measurement technology based on image matching, which compares the texture images of the component surface before and after deformation to measure the displacement and strain information. However, the traditional digital image correlation method is severely dependent on the surface texture information of the component, and the measurement accuracy is easily affected by various complex disturbances. Especially when facing the complex component surface with high reflectivity or weak texture, the measurement accuracy and robustness will decrease significantly. Moreover, the digital image correlation method can only provide displacement and strain information, and cannot directly obtain the three-dimensional morphology data of the component. In general, the existing measurement technology cannot realize the synchronous measurement of the morphology, displacement and strain of the complex component, and the measurement accuracy is easily affected by environmental factors. Therefore, a new measurement method is needed to synchronously obtain multi-dimensional information and improve the measurement accuracy and robustness. SUMMARY

[0003] The present application provides a component multi-dimensional information measurement method and system based on multi-source information fusion to solve the technical problems mentioned in the background.

[0004] To achieve the above purpose, the technical scheme of the present application is as follows:

[0005] The present application provides a component multi-dimensional information measurement method based on multi-source information fusion, comprising the following steps:

[0006] S1, obtaining the fluorescent speckle image before deformation and the texture image, and decomposing both images into low-frequency features and high-frequency features by discrete wavelet transform;

[0007] S2, locally varing the dynamic weight fusion of the low-frequency features of the fluorescent speckle image before deformation and the texture image before deformation; locally varing the energy weighted fusion of the high-frequency features of the fluorescent speckle image before deformation and the texture image before deformation; obtaining the fused low-frequency features and high-frequency features before deformation;

[0008] S3, reconstructing the low-frequency feature and the high-frequency feature of the pre-deformation fused image through inverse wavelet transform to obtain a pre-deformation fused image;

[0009] S4, obtaining a post-deformation fused image by using the same method as S1 to S3;

[0010] S5, acquiring a three-dimensional topography of the component by using a fringe projection profilometry (FPP), calculating a sub-pixel level displacement field, constructing a three-dimensional displacement field according to the three-dimensional topography and the sub-pixel level displacement field, extracting partial derivatives of the three-dimensional displacement field with respect to pixel coordinates, calculating a Green strain tensor based on the partial derivatives and a differential chain rule, and the three-dimensional topography, the three-dimensional displacement field and the Green strain tensor constituting multi-dimensional information of the component.

[0011] Further, the S1 specifically comprises the following steps:

[0012] S11, uniformly spraying the fluorescent material on the surface of the pre-deformation component, and acquiring a pre-deformation fluorescent speckle image by using a camera , a texture image ; for the pixel coordinates of the pre-deformation image;

[0013] S12, decomposing the pre-deformation fluorescent speckle image into a low-frequency feature of the pre-deformation fluorescent speckle image and high-frequency features of the pre-deformation fluorescent speckle image in horizontal, vertical and diagonal directions through discrete wavelet transform;

[0014] S13, decomposing the pre-deformation texture image into a low-frequency feature of the pre-deformation texture image and three high-frequency features of the pre-deformation texture image in horizontal, vertical and diagonal directions through discrete wavelet transform.

[0015] Further, the S2 specifically comprises the following steps:

[0016] S21, performing local variance dynamic weight fusion on the low-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image to obtain a fused low-frequency feature, and the calculation formula is specifically as follows:

[0017] ;

[0018] wherein, represents the fused low-frequency feature; , respectively represent the low-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image; , respectively represent the weights corresponding to the low-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image;

[0019] S22, the high frequency characteristic parameters of the speckle image before deformation and the texture image before deformation are fused by local energy weighted fusion to obtain three fused high frequency characteristics in horizontal, vertical and diagonal directions, and the calculation formula is as follows:

[0020] ;

[0021] ;

[0022] ;

[0023] , , , are three fused high frequency characteristics in horizontal, vertical and diagonal directions; , , are three high frequency characteristics of the speckle image before deformation in horizontal, vertical and diagonal directions; , , are three high frequency characteristics of the texture image before deformation in horizontal, vertical and diagonal directions; , , are weights corresponding to the three high frequency characteristics of the speckle image before deformation in horizontal, vertical and diagonal directions respectively; , , are weights corresponding to the three high frequency characteristics of the texture image before deformation in horizontal, vertical and diagonal directions respectively.

[0024] Further, the calculation formula of the weights and in S21 is as follows:

[0025] ;

[0026] ;

[0027] In the formula, , respectively represent the local variance of the speckle image before deformation and the texture image in the specified window;

[0028] The calculation formula of the weights and in S22 is as follows:

[0029] ;

[0030] ;

[0031] wherein, , respectively are the local energy of the speckle image and the texture image in the designated window before deformation.

[0032] Further, the calculation formula of the fused image before deformation in S3 is:

[0033] ;

[0034] wherein, represents the fused image before deformation; IDWT represents the inverse discrete wavelet transform.

[0035] Further, S5 specifically comprises the following steps:

[0036] S51, using a measurement system and using fringe projection profilometry (FPP) to obtain the three-dimensional topography of the component;

[0037] S52, dividing the surface of the component into grid cells, and using a zero-mean normalized squared difference correlation algorithm to calculate the matching similarity of the fused images before and after deformation in each grid cell;

[0038] S53, minimizing the matching similarity of the fused images before and after deformation in each grid cell, and screening out high-confidence matching points with a similarity value below a threshold value according to a pre-set similarity threshold value;

[0039] S54, for the high-confidence matching points, using a least squares-based surface fitting algorithm to obtain an initial displacement field distribution, and combining a Gauss-Newton method to iteratively optimize the displacement gradient to obtain a sub-pixel level displacement field ;

[0040] S55, using the three-dimensional topography in S51 to map the two-dimensional pixel displacement in the sub-pixel level displacement field to the three-dimensional space, calculating the three-dimensional displacement vector of all pixel points in the fused image after deformation, and obtaining a three-dimensional displacement field;

[0041] S56, extracting the partial derivative of the three-dimensional displacement field with respect to the pixel coordinates through a differentiable convolution kernel, and calculating the Green strain tensor based on the differential chain rule, the Green strain tensor including normal strain components and shear strain components in x, y, and z axial directions; the three-dimensional topography, the three-dimensional displacement field, and the Green strain tensor constitute the multi-dimensional information of the component.

[0042] Further, the calculation formula of the matching similarity in S52 is:

[0043] ;

[0044] wherein, represents the matching similarity currently calculated; 、 respectively represent the mean gray value of the local window frame in the fused image before and after deformation; 、 respectively represent the standard deviation of the local window frame in the fused image before and after deformation; 、 respectively represent the local gray value of the fused image before and after deformation; 、 respectively represent the horizontal and vertical offset for traversing all pixel positions in the matching window, is the matching window.

[0045] Further, the calculation formula of the three-dimensional displacement vector in S55 is:

[0046] ;

[0047] wherein, is the pixel coordinate of the deformed image, 、 、 is the three-dimensional topography of the corresponding pixel coordinate, 、 、 is the three-dimensional displacement of the corresponding pixel coordinate.

[0048] Further, the calculation formula of the Green strain tensor in S56 is:

[0049] ;

[0050] wherein, 、 、 respectively represent the normal strain components in x, y and z axial directions, 、 、 respectively represent the shear strain components in x, y and z axial directions; represents the partial derivative symbol.

[0051] Another aspect of the present application also provides a component multi-dimensional information measurement system based on multi-source information fusion, comprising a measurement system which performs multi-dimensional information measurement according to the above component multi-dimensional information measurement method.

[0052] The present application has the following advantages:

[0053] 1. The application fuses the fluorescent speckle image and the texture image by using discrete wavelet transform, fully combines the contrast information in the high-frequency feature of the fluorescent speckle image and the structural information in the low-frequency feature of the texture image, effectively overcomes the interference of environmental factors on displacement and strain measurement, and improves the measurement accuracy and robustness.

[0054] 2. The application combines the fringe projection profilometry, the zero-mean normalized square difference correlation algorithm and the calculation based on the differential chain rule to obtain the Green strain tensor (including normal strain components and shear strain components in x, y and z axial directions), realizes the synchronous measurement of the three-dimensional morphology, displacement and strain of the complex component, and significantly improves the robustness and accuracy of multidimensional information measurement. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The generation flowchart of the fused image in the application is shown in the figure;

[0056] Figure 2 The flowchart of the multidimensional information measurement in the application is shown in the figure. DETAILED DESCRIPTION

[0057] In order to facilitate the understanding of the application, the application will be described more fully below with reference to the related drawings. The preferred embodiments of the application are shown in the drawings. However, the application can be realized in many other different forms, and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive.

[0058] With reference to Figure 1 and Figure 2 , the embodiment of the application provides a component multidimensional information measurement method based on multi-source information fusion, which is suitable for synchronous high-precision measurement of complex component surface morphology, displacement and strain; specifically including the following steps:

[0059] S1, obtaining a fluorescent speckle image before deformation and a texture image, decomposing both images into low-frequency features and high-frequency features through discrete wavelet transform;

[0060] S2, taking local variance dynamic weight fusion on the low-frequency features of the fluorescent speckle image before deformation and the texture image before deformation; taking local energy weight fusion on the high-frequency features of the fluorescent speckle image before deformation and the texture image before deformation; obtaining the fused low-frequency features and high-frequency features before deformation;

[0061] S3, reconstructing the fused low-frequency features and high-frequency features before deformation through inverse wavelet transform to obtain a fused image before deformation;

[0062] S4, obtaining a fused image after deformation by using the same method as S1 to S3;

[0063] S5, acquiring three-dimensional topography of the component by using fringe projection profilometry (FPP); calculating sub-pixel level displacement field, constructing three-dimensional displacement field according to the three-dimensional topography and the sub-pixel level displacement field; extracting partial derivatives of the three-dimensional displacement field to the pixel coordinates, and calculating Green strain tensor based on the partial derivatives and on differential chain rule, the three-dimensional topography, the three-dimensional displacement field and the Green strain tensor constituting multi-dimensional information of the component.

[0064] The application fuses the fluorescent speckle image and the texture image by using the discrete wavelet transform, fully combines contrast information in high-frequency features of the fluorescent speckle image and structure information in low-frequency features of the texture image, effectively overcomes interference of environmental factors on displacement and strain measurement, and improves measurement accuracy and robustness.

[0065] In some embodiments, with reference to Figure 1 , the S1 specifically comprises the following steps:

[0066] S11, uniformly spraying the colorless, odorless and non-toxic fluorescent material on the surface of the component before deformation, overcoming the problem of large reflectivity difference of traditional speckles by using the self-blanking property of the material; and acquiring the fluorescent speckle image before deformation by using a camera , a texture image ; is the pixel coordinate of the image before deformation;

[0067] S12, decomposing the fluorescent speckle image before deformation into low-frequency features of the fluorescent speckle image and high-frequency features of the fluorescent speckle image in horizontal, vertical and diagonal directions by using Haar as a wavelet base, to realize information decomposition of multiple source images (i.e., the fluorescent speckle image and the texture image), specifically as follows:

[0068] ;

[0069] Wherein, DWT represents discrete wavelet transform;

[0070] S13, decomposing the texture image before deformation into low-frequency features of the texture image and three high-frequency features of the texture image in horizontal, vertical and diagonal directions by using discrete wavelet transform, specifically as follows:

[0071] .

[0072] In some embodiments, with reference to Figure 1 , the S2 specifically comprises the following steps:

[0073] S21, performing local variance dynamic weight fusion on the low-frequency features of the fluorescent speckle image before deformation and the texture image before deformation to obtain fused low-frequency features, and the calculation formula is specifically as follows:

[0074] ;

[0075] wherein, represents the fused low-frequency feature; , respectively represent the low-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image; , respectively represent the weights corresponding to the low-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image;

[0076] S22, the high-frequency features of the pre-deformation fluorescent speckle image and the pre-deformation texture image are fused by local energy weighted fusion to obtain three fused high-frequency features in horizontal, vertical and diagonal directions, and the calculation formula is specifically as follows:

[0077] ;

[0078] ;

[0079] ;

[0080] wherein, , , are three fused high-frequency features in horizontal, vertical and diagonal directions; , , are three high-frequency features of the pre-deformation fluorescent speckle image in horizontal, vertical and diagonal directions; , , are three high-frequency features of the pre-deformation texture image in horizontal, vertical and diagonal directions; , , respectively are the weights corresponding to the three high-frequency features of the pre-deformation fluorescent speckle image in horizontal, vertical and diagonal directions; , , respectively are the weights corresponding to the three high-frequency features of the pre-deformation texture image in horizontal, vertical and diagonal directions.

[0081] In some embodiments, the calculation formula of the weights and the weight is specifically as follows:

[0082] ;

[0083] ;

[0084] wherein, , respectively represent the local variance of the speckle image and the texture image before deformation in a specified window;

[0085] The calculation formula of the weight and the weight is specifically as follows:

[0086] ;

[0087] ;

[0088] wherein, , respectively represent the local energy of the speckle image and the texture image before deformation in a specified window.

[0089] In some embodiments, the calculation formula of the fused image before deformation in S3 is as follows:

[0090] ;

[0091] wherein, represents the fused image before deformation; IDWT represents the inverse discrete wavelet transform.

[0092] In some embodiments, referring to Figure 2 , S5 specifically comprises the following steps:

[0093] S51, obtaining the three-dimensional topography of the component by using a measurement system and using the fringe projection profilometry (FPP); the measurement system comprises a projector and a camera;

[0094] S52, dividing the surface of the component into grid units, and calculating the matching similarity of the fused images before and after deformation in each grid unit by using a zero-mean normalized square difference correlation algorithm;

[0095] S53, minimizing the matching similarity of the fused images before and after deformation in each grid unit, and screening out high-confidence matching points with a similarity value lower than a threshold value according to a preset similarity threshold value;

[0096] S54, for the high-confidence matching points, obtaining an initial displacement field distribution by using a least square-based surface fitting algorithm, and iteratively optimizing the displacement gradient by using a Gauss-Newton method to obtain a sub-pixel level displacement field ;

[0097] S55, mapping the two-dimensional pixel displacement in the sub-pixel level displacement field to a three-dimensional space by using the three-dimensional topography in S51, calculating the three-dimensional displacement vector of all pixel points in the fused image after deformation, and obtaining a three-dimensional displacement field.

[0098] S56, extract partial derivatives of the pixel coordinates by the micro-convolution kernel, and calculate the Green strain tensor based on the differential chain rule, the Green strain tensor including normal strain components and shear strain components in x, y, and z axial directions; the three-dimensional topography, the three-dimensional displacement field, and the Green strain tensor constitute multi-dimensional information of the component.

[0099] In some embodiments, the calculation formula of the matching similarity in S52 is:

[0100] ;

[0101] wherein, represents the matching similarity calculated at present; , are the average gray values of the local window frame in the fusion images before and after deformation, respectively; , are the standard deviations of the local window frame in the fusion images before and after deformation, respectively; , respectively represent the local gray values of the fusion images before and after deformation; , respectively represent the horizontal and vertical offset amounts for traversing all pixel positions in the matching window, is the matching window.

[0102] In some embodiments, the calculation formula of the three-dimensional displacement vector in S55 is:

[0103] ;

[0104] wherein, is the pixel coordinate of the deformed image, , , is the three-dimensional topography of the corresponding pixel coordinate, , , is the three-dimensional displacement of the corresponding pixel coordinate.

[0105] In some embodiments, the calculation formula of the Green strain tensor in S56 is:

[0106] ;

[0107] wherein, , , are normal strain components in x, y, and z axial directions, respectively, , , are shear strain components in three axial directions of x, y, z respectively; denotes a partial derivative symbol.

[0108] The present application combines fringe projection profilometry (FPP), zero-mean normalized square difference correlation algorithm and Green strain tensor (including normal strain components and shear strain components in three axial directions of x, y, z) calculated based on differential chain rule to realize synchronous measurement of three-dimensional morphology, displacement and strain of a complex component, and significantly improve the robustness and accuracy of multi-dimensional information measurement.

[0109] Another aspect of the present application also provides a component multi-dimensional information measurement system based on multi-source information fusion, which comprises a measurement system for performing multi-dimensional information measurement according to the above component multi-dimensional information measurement method.

[0110] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Moreover, the technical solutions of each embodiment of the present application can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the protection scope required by the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for measuring multi-dimensional information of a component based on multi-source information fusion, characterized in that, It comprises the following steps: S1, obtaining the speckle pattern image before deformation and the texture image, and decomposing the two images into low-frequency features and high-frequency features through discrete wavelet transform; S2, taking local variance dynamic weight fusion on the low-frequency features of the speckle pattern image before deformation and the texture image before deformation; taking local energy weight fusion on the high-frequency features of the speckle pattern image before deformation and the texture image before deformation; obtaining the fused low-frequency features and high-frequency features before deformation; S3, reconstructing the fused low-frequency features and high-frequency features before deformation through inverse wavelet transform to obtain the fused image before deformation; S4, obtaining the fused image after deformation by using the same method as S1 to S3; S5, obtaining the three-dimensional morphology of the component by using the fringe projection profilometry (FPP), calculating the sub-pixel level displacement field, constructing the three-dimensional displacement field according to the three-dimensional morphology and the sub-pixel level displacement field, extracting the partial derivative of the three-dimensional displacement field to the pixel coordinates, and calculating the Green strain tensor based on the differential chain rule through the partial derivative, wherein the three-dimensional morphology, the three-dimensional displacement field and the Green strain tensor constitute the multi-dimensional information of the component. 2.The method according to claim 1, wherein, The S1 specifically comprises the following steps: S11, uniformly spray the fluorescent material on the surface of the component before deformation, and acquire the fluorescent speckle image before deformation through a camera , texture image ; is the image pixel coordinate before deformation; S12, the fluorescent speckle image before deformation decomposition into low-frequency features of the fluorescent speckle image and high-frequency features of the fluorescent speckle image in horizontal, vertical and diagonal directions by discrete wavelet transform S13, the texture image before deformation The texture image is decomposed into a low frequency feature and three high frequency features in horizontal, vertical and diagonal directions by discrete wavelet transform. 3.The method according to claim 2, wherein, The S2 specifically comprises the following steps: S21, taking local variance dynamic weight fusion on the low-frequency features of the speckle pattern image before deformation and the texture image before deformation, and obtaining the fused low-frequency features, wherein the calculation formula is specifically as follows: ； wherein, denotes the low-frequency feature after fusion; , denote the low-frequency features of the fluorescent speckle image before deformation and the texture image before deformation, respectively; , denote the weights corresponding to the low-frequency features of the fluorescent speckle image before deformation and the texture image before deformation, respectively. S22, taking local energy weight fusion on the high-frequency features of the speckle pattern image before deformation and the texture image before deformation, and obtaining three fused high-frequency features in the horizontal, vertical and diagonal directions, wherein the calculation formula is specifically as follows: ； ； ； wherein, , , are three high frequency features of the fused image in horizontal, vertical and diagonal directions; , , are three high frequency features of the deformed speckle image in horizontal, vertical and diagonal directions; , , are three high frequency features of the deformed texture image in horizontal, vertical and diagonal directions; , , are weights corresponding to the three high frequency features of the deformed speckle image in horizontal, vertical and diagonal directions, respectively; , , are weights corresponding to the three high frequency features of the deformed texture image in horizontal, vertical and diagonal directions, respectively.

4. The multi-source information fusion based component multi-dimension information measurement method according to claim 3, characterized in that, The weight in the S21 and the weight The calculation formula is as follows: ； ； wherein, , respectively denote the local variances of the speckle image and the texture image in the designated window before deformation. The weight in S22 and the weight The calculation formula is as follows: ； ； wherein, , are the local energies of the speckle image and the texture image, respectively, in the specified window before deformation.

5. The multi-source information fusion based component multi-dimension information measurement method according to claim 4, characterized in that, The calculation formula of the fused image before deformation in the S3 is: ； wherein denotes the fused image before morphing; denotes the inverse discrete wavelet transform.

6. The component multi-dimension information measurement method based on multi-source information fusion according to claim 5, characterized in that, The S5 specifically comprises the following steps: S51, obtaining the three-dimensional morphology of the component by using the measurement system and using the fringe projection profilometry (FPP); S52, dividing the surface of the component into grid units, and calculating the matching similarity of the fused images before and after deformation in each grid unit by using the zero-mean normalized square difference correlation algorithm; S53, minimizing the matching similarity of the fused images before and after deformation in each grid unit, and screening out high-confidence matching points with a similarity value lower than a threshold value according to a preset similarity threshold value; S54, for high confidence matching points, an initial displacement field distribution is obtained by using a least square based surface fitting algorithm, and the displacement gradient is iteratively optimized by combining a Gauss-Newton method to obtain a sub-pixel level displacement field ; S55, using the three-dimensional topography in S51, map the two-dimensional pixel displacement in the sub-pixel level displacement field to the three-dimensional space, and calculate the three-dimensional displacement vector of all pixel points in the fused image after deformation to obtain a three-dimensional displacement field; S56, extracting the partial derivative of the three-dimensional displacement field to the pixel coordinates through the differentiable convolution kernel, and calculating the Green strain tensor based on the differential chain rule, wherein the Green strain tensor comprises normal strain components and shear strain components in x, y and z axial directions; the three-dimensional morphology, the three-dimensional displacement field and the Green strain tensor constitute the multi-dimensional information of the component.

7. The component multi-dimension information measurement method based on multi-source information fusion according to claim 6, characterized in that, The calculation formula of the matching similarity in the S52 is: ； wherein, represents the matching similarity currently calculated; , are the mean gray values of the local window frame in the fusion image before and after deformation, respectively; , are the standard deviations of the local window frame in the fusion image before and after deformation, respectively; , respectively represent the local gray values of the fusion image before and after deformation; , represent the horizontal and vertical offset amounts for traversing all pixel positions in the matching window, is the matching window. 8.The method according to claim 7, wherein, The calculation formula of the three-dimensional displacement vector in the S55 is: ； wherein, is the pixel coordinate of the deformed image, , , is the three-dimensional topography of the corresponding pixel coordinate, , , is the three-dimensional displacement of the corresponding pixel coordinate.

9. The multi-source information fusion based component multi-dimension information measurement method according to claim 8, characterized in that, The calculation formula of the Green strain tensor in the S56 is: ； wherein, , , are the normal strain components in the x, y, z axial directions, respectively, , , are the shear strain components in the x, y, z axial directions, respectively; denotes the partial derivative symbol.

10. A multi-source information fusion-based component multi-dimension information measurement system, characterized in that, The measurement system measures the multi-dimensional information of the component according to the component multi-dimensional information measurement method in any one of claims 1 to 9.

Images