Fracture section image analysis device and fracture section image analysis method

Abstract

To provide a fracture section image analysis device and a fracture section image analysis method that are capable of performing highly accurate analysis.SOLUTION: According to an embodiment, a fracture section image analysis device includes: an acquisition unit configured to acquire a first image including a fracture section of a component; and a processing unit configured to perform image analysis for the first image. The image analysis includes first processing and second processing. The first processing includes deriving a plurality of fracture progress directions in the fracture section. One of the plurality of fracture progress directions corresponds to one of a plurality of positions included in the fracture section. The second processing includes deriving a fracture origin position in the fracture section based on at least a part of the plurality of fracture progress directions.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to a fracture surface image analysis apparatus and a fracture surface image analysis method.

Background Art

[0002] For example, analysis of a member is performed based on an image such as a fracture surface of the member. Higher-precision analysis is desired.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Embodiments provide a fracture surface image analysis apparatus and a fracture surface image analysis method capable of high-precision analysis.

Means for Solving the Problems

[0005] According to an embodiment, a fracture surface image analysis apparatus includes an acquisition unit configured to acquire a first image including a fracture surface of a member, and a processing unit configured to execute image analysis on the first image. The image analysis includes a first process and a second process. The first process includes deriving a plurality of fracture propagation directions in the fracture surface. One of the plurality of fracture propagation directions corresponds to one of a plurality of positions included in the fracture surface. The second process includes deriving a fracture origin position in the fracture surface based on at least a part of the plurality of fracture propagation directions.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

[0007] Hereinafter, each embodiment of the present invention will be described with reference to the drawings. The drawings are schematic or conceptual, and the relationship between the thickness and width of each part, the ratio of the sizes between parts, etc. are not necessarily the same as those in reality. Even when representing the same part, the dimensions and ratios may be represented differently in the drawings. In the present specification and each figure, the same reference numerals are given to the same elements as those described above with respect to the previously shown figures, and the detailed description will be omitted as appropriate.

[0008] (First Embodiment) FIG. 1 is a flowchart exemplifying the operation of a cross-sectional image analysis apparatus according to the first embodiment. FIG. 2 is a schematic diagram exemplifying the cross-sectional image analysis apparatus according to the first embodiment. As shown in FIG. 2, the cross-sectional image analysis apparatus 110 according to the embodiment includes an acquisition unit 75 and a processing unit 70. The acquisition unit 75 is configured to acquire a first image 71D. The acquisition unit 75 may be, for example, an interface or the like. The processing unit 70 is configured to perform image analysis on the first image 71D. The cross-sectional image analysis apparatus 110 may be, for example, an image processing apparatus.

[0009] The processing unit 70 may be, for example, an electric circuit. The processing unit 70 may be, for example, a computer or the like. The processing unit 70 may include, for example, a CPU (central processing unit) or the like. The processing unit 70 may include, for example, a GPU (graphics processing unit) or the like.

[0010] As shown in FIG. 2, the cross-sectional image analysis apparatus 110 may include a GUI (Graphical User Interface) 79a. The cross-sectional image analysis apparatus 110 may include a display 79b. The GUI 79a may display the target content on the display 79b. The cross-sectional image analysis apparatus 110 may include an input unit 79c and a storage 79d or the like. The input unit 79c may include, for example, at least one of a keyboard, a mouse, a touch panel, and a voice input device or the like. The storage 79d can store a part of the data used for processing or at least a part of the processing result.

[0011] The first image 71D acquired by the acquisition unit 75 includes the fracture surface of the member 81. The first image 71D may be obtained, for example, from an imaging device 50 that images the fracture surface of the member 81. The location where the imaging device 50 is provided may be different from the location where the fracture surface image analysis device 110 is provided. The location where the imaging device 50 is provided may be the same as the location where the fracture surface image analysis device 110 is provided. The analysis device 210 according to the embodiment may include the fracture surface image analysis device 110 and the imaging device 50. The imaging device 50 may be regarded as being included in the fracture surface image analysis device 110. Information regarding the first image 71D may be supplied to the acquisition unit 75 by any method such as wired or wireless. For example, information regarding the first image 71D may be stored in an arbitrary memory (such as the storage 79d), and the stored information may be supplied to the acquisition unit 75.

[0012] The first image 71D may include, for example, a microscopic photograph (e.g., SEM: Scanning Electron Microscope) image of the fracture surface of the member 81. The member 81 may include, for example, at least one of resin and metal. The member 81 may be a component included in various devices. The component may be damaged. By analyzing the fractured fracture surface, the cause of the fracture and the like can be identified. The analysis of the fracture surface may be performed during the development stage, design stage, manufacturing stage, or after-sales stage of various devices.

[0013] As shown in FIG. 1, the image processing performed by the processing unit 70 includes a first process (step S110) and a second process (step S120). The first process includes deriving (e.g., estimating) a plurality of fracture propagation directions at the fracture surface. One of the plurality of fracture propagation directions corresponds to one of the plurality of positions included in the fracture surface. As will be described later, the first image may be divided into a plurality of patch regions. The fracture propagation direction in each of the plurality of patch regions is derived. The plurality of patch regions may be, for example, rectangular.

[0014] The second process includes deriving a fracture initiation position on the fracture surface based on at least a part of a plurality of fracture propagation directions. For example, by deriving the fracture initiation position, the fracture mechanism can be derived with high accuracy. For example, by obtaining information regarding the fracture initiation position, it becomes easier to obtain guidelines such as design changes for the target member 81 (such as parts).

[0015] For example, there is a reference example of estimating a fracture mode or the like based on an image of the fracture surface. The fracture mode is, for example, ductile fracture, fatigue fracture, brittle fracture, solvent crack, or intergranular fracture. In this reference example, even if the fracture mode can be specified, the position of the starting point where the fracture occurs is not derived. Therefore, the accuracy of the analysis is low.

[0016] In contrast, in the embodiment, the fracture propagation direction is derived. That is, the progress of the fracture (temporal change in the fracture position) in the target member 81 is estimated. Thereby, the fracture mechanism in the target member 81 can be grasped more accurately. According to the embodiment, an image analysis apparatus capable of high-precision analysis can be provided.

[0017] In the embodiment, further, the fracture initiation position is derived. The fracture initiation position corresponds to, for example, the starting point of the fracture in the target member 81. By specifying the fracture initiation position, the fracture mechanism in the target member 81 can be derived with higher accuracy. For the target member 81, more accurate design changes become easier. According to the embodiment, an image analysis apparatus capable of higher-precision analysis can be provided.

[0018] For example, as will be described later, one of the plurality of fracture propagation directions can be represented by an angle θ. The angle θ is 0 degrees or more and less than 360 degrees. One of the plurality of fracture propagation directions may be represented by sin θ and cos θ. By processing information (value group) regarding the plurality of fracture propagation directions, the position serving as the starting point of the plurality of fracture propagation directions can be derived. The derived position becomes the fracture initiation position.

[0019] As shown in FIG. 1, in the embodiment, at least a part obtained by the analysis process may be displayed by the GUI (step S130).

[0020] As shown in FIG. 2, the processing unit 70 may include a plurality of processing parts (such as a first processing part 70a and a second processing part 70b). The plurality of processing parts may correspond to a plurality of models, for example. The number of the plurality of processing parts is arbitrary.

[0021] In the embodiment, the first process may include deriving one fracture propagation direction in the fracture plane. The second process may include deriving a fracture starting point position in the fracture plane based on the fracture propagation direction. In the second process, for example, other information (such as known information regarding the fracture propagation direction and the fracture starting point position) may be used to derive the fracture starting point position.

[0022] Hereinafter, an example of the first process will be described. FIG. 3 is a schematic diagram illustrating a part of the operation of the fracture plane image analysis apparatus according to the first embodiment. As shown in FIG. 3, for example, the first image 71D acquired by the acquisition unit 75 is supplied to the processing unit 70. For example, the processing unit 70 includes a divider 71 and a first processing part 70a. The divider 71 divides the first image 71D into a plurality of patch regions 71P. Information regarding the images included in each of the plurality of patch regions 71P obtained by the division is supplied to the first processing part 70a. In the first processing part 70a, the fracture propagation direction Dr1 in each of the plurality of patch regions 71P is derived.

[0023] The first processing part 70a derives the fracture propagation direction Dr1 by, for example, a processing model based on deep learning. The first processing part 70a performs, for example, processing based on machine learning. The processing based on machine learning is performed using, for example, one of a plurality of models 72M. The plurality of models 72M are, for example, pre-trained models.

[0024] The first processing part 70a corresponds to, for example, a regression processing unit. The regression processing unit is configured to perform processing based on machine learning related to a plurality of teacher images including the fracture surface of the member 81 and a plurality of fracture progression directions Dr1. The first processing includes the processing by such a regression processing unit (the first processing part 70a).

[0025] As shown in FIG. 3, for example, at least any one of information regarding the fracture mode 72a of the fracture surface, information regarding the material 72b of the member 81, information regarding the shape 72c of the member 81, and information regarding the molding condition 72d of the member 81 is supplied to the processing unit 70. The processing unit 70 includes a model selector 72. The above information is supplied to the model selector 72.

[0026] The model selector 72 selects one of a plurality of models 72M to be used in the processing based on the fracture mode 72a, the material 72b, the shape 72c, the molding condition 72d, and the like. Information regarding the selected model 72M is supplied to the first processing part 70a. The first processing part 70a derives the fracture progression direction Dr1 in each of the plurality of patch regions 71P using the selected model 72M.

[0027] In this way, the processing unit 70 may include a plurality of models 72M. The plurality of models 72M includes a first model 72A, a second model 72B, and the like. For example, in one operation (the first operation), the processing unit 70 performs the first processing using one of the plurality of models 72M (the first model 72A). In another operation (the second operation), the processing unit 70 performs the first processing using another one of the plurality of models 72M (the second model 72B). At least one of the fracture mode 72a of the fracture surface, the material 72b of the member 81, the shape 72c of the member 81, and the molding condition 72d of the member 81 is different between one of the plurality of models 72M and another one of the plurality of models 72M.

[0028] Depending on at least one difference among the fracture mode 72a of the fracture surface, the material 72b of the member 81, the shape 72c of the member 81, and the molding conditions 72d of the member 81, one of a plurality of appropriate models 72M is selected. By using an appropriate model, more accurate processing can be performed.

[0029] The first processing part 70a derives the fracture propagation direction Dr1 for each of the plurality of patch regions 71P by using one of the plurality of selected models 72M. In this way, the first processing includes deriving one of the plurality of fracture propagation directions Dr1 for one of the plurality of patch regions 71P obtained by dividing the first image 71D acquired by the acquisition part 75.

[0030] The processing part 70 outputs at least a part of the derived plurality of fracture propagation directions Dr1.

[0031] The processing part 70 may output a confidence level CN1 for each of the plurality of fracture propagation directions Dr1. In this way, the first processing may further include deriving a confidence level CN1 for each of the plurality of derived fracture propagation directions Dr1. As will be described later, the processing part 70 may perform a second processing according to the confidence level CN1. The confidence level CN1 for one of the plurality of fracture propagation directions Dr1 may be derived from two or more of the plurality of fracture propagation directions Dr1.

[0032] Hereinafter, an example of the second processing will be described. FIG. 4 is a schematic diagram illustrating a part of the operation of the fracture surface image analysis apparatus according to the first embodiment. FIG. 4 shows an example of the second process. As shown in FIG. 4, the processing unit 70 may include a patch extractor 74 and a second processing portion 70b. For example, a plurality of fracture propagation directions Dr1 and confidence levels CN1 are supplied to the patch extractor 74. The patch extractor 74 extracts at least a part of the plurality of patch regions 71P used for deriving the fracture starting point position SP1 based on the confidence level CN1. Or, the patch extractor 74 extracts at least a part of the plurality of patch regions 71P not used for deriving the fracture starting point position SP1 based on the confidence level CN1. By the operation of the patch extractor 74, a part (post-extraction fracture propagation direction Dr2) of the plurality of fracture propagation directions Dr1 used for deriving the fracture starting point position SP1 is extracted.

[0033] For example, there are a plurality of fracture propagation directions Dr1 (post-extraction fracture propagation direction Dr2) having a confidence level CN1 equal to or higher than a determined reference value. The second processing portion 70b derives the fracture starting point position SP1 using the post-extraction fracture propagation direction Dr2.

[0034] On the other hand, for example, the confidence level CN1 of at least one of the plurality of fracture propagation directions Dr1 is less than a determined reference value. The second processing portion 70b derives the fracture starting point position SP1 without using at least one of such a plurality of fracture propagation directions Dr1. The confidence level CN1 corresponding to this at least one of the plurality of fracture propagation directions Dr1 not used is less than a determined reference value.

[0035] By not using data with a low confidence level CN1, the fracture starting point position SP1 can be derived with higher accuracy.

[0036] In the derivation of the fracture initiation position SP1, defined coordinates (reference coordinates 70C) may be used. As already explained, for example, the first image 71D is obtained from an imaging device 50 that images the fracture surface of the member 81 (see FIG. 2). The reference coordinates 70C are, for example, the reference coordinates at the time of imaging by the imaging device 50. The reference coordinates 70C at the time of imaging by the imaging device 50 may be, for example, the coordinates set on the stage where the imaging device 50 is provided. The second process may include deriving the fracture initiation position SP1 using common coordinates (reference coordinates 70C) for a plurality of fracture propagation directions Dr1. By processing the plurality of fracture propagation directions Dr1 using common coordinates (reference coordinates 70C), the fracture initiation position SP1 can be derived with high accuracy.

[0037] FIGS. 5(a) to 5(f) are schematic diagrams illustrating the operation of the fracture surface image analysis device according to the first embodiment. FIGS. 5(a) and 5(b) relate to the first sample SPL1. FIGS. 5(c) and 5(d) relate to the second sample SPL2. FIGS. 5(e) and 5(f) relate to the third sample SPL3. FIGS. 5(a), 5(c) and 5(e) correspond to the first image 71D of these samples (fracture surfaces). FIG. 5(b) shows a plurality of fracture propagation directions Dr1 derived from the first image 71D of FIG. 5(a). FIG. 5(d) shows a plurality of fracture propagation directions Dr1 derived from the first image 71D of FIG. 5(c). FIG. 5(f) shows a plurality of fracture propagation directions Dr1 derived from the first image 71D of FIG. 5(e).

[0038] For example, the first image 71D is divided into a plurality of patch regions 71P (see FIG. 3). In each of the plurality of divided patch regions 71P, one of the plurality of fracture propagation directions Dr1 is derived by the first processing portion 70a based on the machine learning model.

[0039] In this example, the first sample SPL1 corresponds to ductile fracture. The second sample SPL2 corresponds to fatigue fracture. The third sample SPL3 corresponds to brittle fracture. These different types of fracture modes correspond to the fracture mode 72a (see FIG. 3). Depending on the difference in the fracture modes, one of the plurality of models 72M is selected, and a plurality of fracture propagation directions Dr1 are derived.

[0040] FIGS. 6(a) and 6(b) are schematic diagrams illustrating the operation of the fracture surface image analysis apparatus according to the first embodiment. FIG. 6(a) illustrates the first image 71D. FIG. 6(b) illustrates a plurality of fracture propagation directions Dr1 derived from the first image 71D of FIG. 6(a) and a fracture origin position SP1 derived from the plurality of fracture propagation directions Dr1.

[0041] As shown in FIG. 6(b), a plurality of fracture propagation directions Dr1 are derived with respect to the first image 71D. In this example, the plurality of fracture propagation directions Dr1 are indicated by the arrow Ar1. For example, if one arrow Ar1 is selected and there is "another arrow Ar2" on the starting side of that arrow Ar1, then that "another arrow Ar2" is taken as the new arrow. For the new arrow, if there is "yet another arrow" on the starting side of the new arrow, then that "yet another arrow" is taken as the new arrow. By repeating such an operation, with respect to the initially selected arrow Ar1, the starting arrow As1 is determined. Such an operation is performed for a plurality of fracture propagation directions Dr1 (a plurality of arrows) arranged two-dimensionally. By the repeated operation, a plurality of starting arrows As1 are derived. The intersection of the extension lines of each of the plurality of arrows As1 can be estimated as the fracture origin position SP1.

[0042] FIG. 7 is a flowchart illustrating the operation of the fracture surface image analysis apparatus according to the first embodiment. Figure 7 illustrates the second process (step S120). In this example, a plurality of fracture propagation directions Dr1 are represented as a plurality of arrows. For example, as one of the plurality of fracture propagation directions Dr1, one of the plurality of arrows (for example, arrow Ar1) is selected (step S121). It is determined whether there is another arrow (for example, arrow Ar2) on the starting point side of the selected arrow Ar1 (step S122). If there is another arrow (for example, arrow Ar2), move to the other arrow Ar2 (step S123). In step S122, if there is no other arrow Ar2, the process proceeds to step S124.

[0043] In step S124, it is determined whether there are any remaining arrows. If there are remaining arrows, the process returns to step S121 and an arrow is selected. By steps S121 and S122, the starting arrow As1 for one of the plurality of arrows (for example, arrow Ar1) initially selected is derived (step S128).

[0044] By repeating the process including steps S121, S122, S123, and S124, a plurality of starting arrows As1 are derived for the plurality of fracture propagation directions Dr1 arranged two-dimensionally.

[0045] In step S124, if there are no remaining arrows, the process proceeds to step S125. In step S125, the intersection of the extensions of the plurality of starting arrows As1 is calculated. The intersection is output, for example, as the fracture starting point position SP1.

[0046] Figure 8 is a schematic diagram illustrating the operation of the fracture cross-sectional image analysis apparatus according to the first embodiment. Figure 8 shows an example of a method for deriving the fracture starting point position SP1 based on a plurality of fracture propagation directions Dr1. As shown in Figure 8, the plurality of fracture propagation directions Dr1 include a first direction D1, a second direction D2, and a third direction D3. The first direction D1 is the direction from the first starting point S1 to the first end point E1. The second direction D2 is the direction from the second starting point S2 to the second end point E2. The third direction D3 is the direction from the third starting point S3 to the third end point E3.

[0047] The position of the second end point E2 on the straight line Ln1 along the first direction D1 is between the position of the second starting point S2 on the straight line Ln1 and the position of the first end point E1 on the straight line Ln1. The position of the first starting point S1 on the straight line Ln1 is between the position of the second end point E2 on the straight line Ln1 and the position of the first end point E1 on the straight line Ln1.

[0048] The first direction D1 corresponds to, for example, the arrow Ar1. The second direction D2 corresponds to another arrow Ar2. Based on the first direction D1, the second direction D2 can be derived. The second direction D2 (another arrow Ar2) is, for example, the closest to the first direction D1 among other directions (other arrows). The angle between the second direction D2 and the straight line Ln1 is smaller than the angle between other directions (other arrows) and the straight line Ln1. Such a second direction D2 can be determined with respect to the first direction D1.

[0049] For example, the second process includes repeatedly performing a starting point derivation process. One of the starting point derivation processes includes specifying the second direction D2 based on the first direction D1. The third direction D3 corresponds to the second direction D2 specified by repeating the starting point derivation process. The second process uses the position on the extension line Ln2 in the direction from the third end point E3 to the third starting point S3 of the third direction D3 obtained by repeating the starting point derivation process as a candidate for the fracture starting point position SP1. By repeating the starting point derivation process, a plurality of extension lines Ln2 are obtained. The intersection of the plurality of extension lines Ln2 becomes the fracture starting point position SP1.

[0050] FIG. 9(a) and FIG. 9(b) are schematic diagrams illustrating the operation of the cross-sectional image analysis apparatus according to the first embodiment. In FIGS. 9(a) and 9(b), the magnifications of the first image 71D are different from each other. The imaging magnification of the first image 71D in FIG. 9(a) is lower than the imaging magnification of the first image 71D in FIG. 9(b). The magnification ratios of the plurality of patch regions 71P in FIG. 9(a) are higher than the magnification ratios of the plurality of patch regions 71P in FIG. 9(b). Thus, the first process may include changing a range included in at least one of the plurality of patch regions 71P according to the imaging magnification of the first image 71D. For example, the input first image 71D is adjusted to a size suitable for a processing model by deep learning. Appropriate processing can be performed with high accuracy.

[0051] FIGS. 10(a) and 10(b) are schematic diagrams illustrating the operation of the cross-sectional image analysis apparatus according to the first embodiment. As shown in FIG. 10(a), for example, a plurality of fracture propagation directions Dr1 are derived for the plurality of patch regions 71P. At this time, one of the plurality of fracture propagation directions Dr1 may be significantly (exceeding a threshold value) different from the others of the plurality of fracture propagation directions Dr1. The others of the plurality of fracture propagation directions Dr1 are adjacent to each other among the plurality of fracture propagation directions Dr1.

[0052] In such a case, as shown in FIG. 10(b), one of the plurality of fracture propagation directions Dr1 that is significantly different (average fracture propagation direction Dra1) may be corrected based on the directions of the other averages. The average fracture propagation direction Dra1 is obtained, for example, by averaging at least a part of the plurality of fracture propagation directions Dr1. The averaging may be, for example, averaging in units of the plurality of patch regions 71P. By using the average fracture propagation direction Dra1, for example, the fracture origin position SP1 can be derived with higher accuracy.

[0053] FIG. 11 is a schematic diagram illustrating the operation of the cross-sectional image analysis apparatus according to the first embodiment. FIG. 11 shows an example of the display by the GUI 79a in the cross-sectional image analysis device 110. For example, a plurality of derived fracture propagation directions Dr1 may be displayed superimposed on the input image (the first image 71D). For example, at least a part of the plurality of fracture propagation directions Dr1 may be filtered and displayed according to the confidence level CN1. For example, a plurality of fracture propagation directions Dr1 may be displayed according to the specified resolution. For example, the fracture origin position SP1 is displayed. The fracture origin position SP1 may be displayed superimposed on the input image (the first image 71D). For example, a plurality of images and the fracture origin position SP1 may be displayed based on the image coordinate system for display.

[0054] As described above, the cross-sectional image analysis device 110 may further include the GUI 79a. The GUI 79a is configured to perform at least any one of a first display operation, a second display operation, a third display operation, a fourth display operation, a fifth display operation, a sixth display operation, and a seventh display operation.

[0055] In the first display operation, the GUI 79a, for example, displays at least a part of the plurality of fracture propagation directions Dr1 superimposed on the first image 71D. In the second display operation, the GUI 79a, for example, selectively displays a part of the plurality of fracture propagation directions Dr1 according to the directions of the plurality of fracture propagation directions Dr1.

[0056] In the third display operation, the GUI 79a, for example, displays a part of the plurality of fracture propagation directions Dr1 in units of the plurality of patch regions 71P. In the fourth display operation, the GUI 79a displays the plurality of fracture propagation directions Dr1 regarding the whole of the first image 71D.

[0057] In the fifth display operation, the GUI 79a, for example, displays the averaged fracture propagation direction Dra1. The averaged fracture propagation direction Dra1 is obtained by averaging at least a part of the plurality of fracture propagation directions Dr1. The averaging method is arbitrary. At least one of the plurality of fracture propagation directions Dr1 before averaging may be displayed.

[0058] In the sixth display operation, the GUI 79a displays a plurality of patch areas 71P in the image coordinate system. In the seventh display operation, the GUI 79a displays the fracture start position SP1.

[0059] The GUI 79a may be configured to perform at least one of the eighth display operation and the ninth display operation. In the eighth display operation, the GUI 79a selectively displays, for example, some of the plurality of fracture propagation directions Dr1 based on the confidence CN1 for each of the plurality of fracture propagation directions Dr1. In the ninth display operation, the GUI 79a selectively displays, for example, some of the plurality of fracture propagation directions Dr1 (e.g., arrow As1) used when deriving the fracture start position SP1.

[0060] In addition to the above, the GUI 79a may display any content. The content includes, for example, conditions related to image processing. The content may include, for example, commands related to image processing.

[0061] (Second Embodiment) The second embodiment relates to a fracture surface image analysis method. The fracture surface image analysis method acquires a first image 71D including the fracture surface of the member 81. The fracture surface image analysis method executes image analysis on the first image 71D. For example, the fracture surface image analysis method executes image analysis on the first image 71D by the processing unit 70. For example, the image analysis includes a first process and a second process. The first process includes deriving a plurality of fracture propagation directions Dr1 on the fracture surface. One of the plurality of fracture propagation directions Dr1 corresponds to one of the plurality of positions (e.g., a plurality of patch areas 71P) included in the fracture surface. The second process includes deriving a fracture start position SP1 on the fracture surface based on at least a part of the plurality of fracture propagation directions Dr1.

[0062] In the fracture surface image analysis method according to the embodiment, at least a part of the operations of the fracture surface image analysis apparatus 110 described with respect to the first embodiment may be applied.

[0063] According to an embodiment, at least a part of the fracture surface image analysis is automated. The analysis of the fracture surface can be performed at high speed and with high accuracy. In the embodiment, based on an image regarding the fracture surface, a plurality of fracture propagation directions Dr1 are derived. Further, a fracture origin position SP1 can be derived from the plurality of fracture propagation directions Dr1. This enables an analysis that is difficult in the image analysis of reference examples by image classification. In one example according to the embodiment, a model suitable for each of different fracture modes is adopted. Higher-accuracy analysis is possible. In the embodiment, even when the first image 71D contains a lot of noise, an appropriate analysis result can be easily obtained. The fracture surface image analysis method according to the embodiment may be, for example, a fracture surface image analysis method. The fracture surface image analysis method according to the embodiment may be, for example, a fracture surface analysis method.

[0064] The embodiment may include the following technical solutions. (Technical solution 1) An acquisition unit configured to acquire a first image including a fracture surface of a member, and A processing unit configured to execute image analysis on the first image, Comprising, The image analysis includes a first process and a second process, The first process includes deriving a plurality of fracture propagation directions in the fracture surface, One of the plurality of fracture propagation directions corresponds to one of a plurality of positions included in the fracture surface, The second process includes deriving a fracture origin position in the fracture surface based on at least a part of the plurality of fracture propagation directions, a fracture surface image analysis device.

[0065] (Technical solution 2) The processing unit includes a plurality of models, In a first operation, the processing unit performs the first process using one of the plurality of models, In a second operation, the processing unit performs the first process using another one of the plurality of models, The fracture surface image analysis device according to Technical Solution 1, wherein at least one of the fracture mode of the fracture surface, the material of the member, the shape of the member, and the molding conditions of the member is different between one of the plurality of models and another one of the plurality of models.

[0066] (Technical Solution 3) The fracture surface image analysis device according to Technical Solution 1 or 2, wherein the first process includes deriving one of the plurality of fracture propagation directions with respect to one of the plurality of patch regions obtained by dividing the first image acquired by the acquisition unit.

[0067] (Technical Solution 4) The fracture surface image analysis device according to Technical Solution 3, wherein the first process includes changing a range included in at least one of the plurality of patch regions according to a magnification of imaging of the first image.

[0068] (Technical Solution 5) The first process further includes deriving a confidence level for each of the derived plurality of fracture propagation directions, The second process includes deriving the fracture starting point position without using at least one of the plurality of fracture propagation directions, and the confidence level corresponding to the at least one of the plurality of fracture propagation directions is less than a determined reference value. The fracture surface image analysis device according to any one of Technical Solutions 1 to 4.

[0069] (Technical Solution 6) The first image is obtained from an imaging device that images the fracture surface, The second process includes deriving the fracture starting point position using common coordinates related to the plurality of fracture propagation directions, The coordinates are reference coordinates at the time of imaging of the imaging device. The fracture surface image analysis device according to any one of Technical Solutions 1 to 5.

[0070] (Technical Solution 7) Further comprising a GUI, The GUI is configured to perform at least one of a first display operation, a second display operation, a third display operation, a fourth display operation, a fifth display operation, a sixth display operation, and a seventh display operation. In the first display operation, the GUI overlays and displays at least a part of the plurality of fracture propagation directions on the first image. In the second display operation, the GUI selectively displays a part of the plurality of fracture propagation directions according to the directions of the plurality of fracture propagation directions. In the third display operation, the GUI displays a part of the plurality of fracture propagation directions in units of the plurality of patch regions. In the fourth display operation, the GUI displays the plurality of fracture propagation directions related to the whole of the first image. In the fifth display operation, the GUI displays an averaged fracture propagation direction, which is obtained by averaging at least a part of the plurality of fracture propagation directions. In the sixth display operation, the GUI displays the plurality of patch regions in an image coordinate system. In the seventh display operation, the GUI displays the fracture starting point position, which is the cross-sectional image analysis device according to Technical Proposal 3 or 4.

[0071] (Technical Proposal 8) Further comprising a GUI, The GUI is configured to perform at least one of an eighth display operation and a ninth display operation. In the eighth display operation, the GUI selectively displays a part of the plurality of fracture propagation directions based on the confidence level for each of the plurality of fracture propagation directions. In the ninth display operation, the GUI selectively displays the part of the plurality of fracture propagation directions used when deriving the fracture starting point position, which is the cross-sectional image analysis device according to any one of Technical Proposals 1 to 4.

[0072] (Technical Proposal 9) The plurality of fracture propagation directions include a first direction, a second direction, and a third direction. The first direction is the direction from the first starting point to the first ending point, The second direction is the direction from the second starting point to the second ending point, The third direction is the direction from the third starting point to the third ending point, The position of the second ending point on the straight line along the first direction is between the position of the second starting point on the straight line and the position of the first ending point on the straight line, The position of the first starting point on the straight line is between the position of the second ending point on the straight line and the position of the first ending point on the straight line, The second process includes repeatedly performing a starting point derivation process, One of the starting point derivation processes includes determining the second direction based on the first direction, The third direction corresponds to the second direction specified by repeating the starting point derivation process, The second process is the cross-section image analysis device according to any one of Technical Solutions 1 to 8, which uses the position of the extension line in the direction from the third ending point to the third starting point as a candidate for the destruction starting point position.

[0073] (Technical Solution 10) The first process includes a process by a regression processing unit configured to perform a process based on machine learning related to a plurality of teacher images including the cross-section and the plurality of destruction progress directions, which is the cross-section image analysis device according to any one of Technical Solutions 1 to 9.

[0074] (Technical Solution 11) Obtain a first image including the cross-section of the member, Execute image analysis on the first image by a processing unit, The image analysis includes a first process and a second process, The first process includes deriving a plurality of destruction progress directions on the cross-section, One of the plurality of destruction progress directions corresponds to one of the plurality of positions included in the cross-section, The second process is a fracture surface image analysis method including deriving a fracture starting point position on the fracture surface based on at least a part of the plurality of fracture propagation directions.

[0075] (Technical Proposal 12) The processing unit includes a plurality of models. In a first operation, the processing unit performs the first process using one of the plurality of models. In a second operation, the processing unit performs the first process using another one of the plurality of models. The fracture surface image analysis method according to Technical Proposal 11, wherein at least one of the fracture mode of the fracture surface, the material of the member, the shape of the member, and the molding conditions of the member is different between the one of the plurality of models and the another one of the plurality of models.

[0076] (Technical Proposal 13) The first process of the fracture surface image analysis method according to Technical Proposal 11 or 12 includes deriving one of the plurality of fracture propagation directions with respect to one of the plurality of patch regions obtained by dividing the first image.

[0077] (Technical Proposal 14) The first process of the fracture surface image analysis method according to Technical Proposal 13 includes changing a range included in at least one of the plurality of patch regions according to a magnification of imaging of the first image.

[0078] (Technical Proposal 15) The first process further includes deriving a confidence level for each of the derived plurality of fracture propagation directions. The second process includes deriving the fracture starting point position without using at least one of the plurality of fracture propagation directions, and the confidence level corresponding to the at least one of the plurality of fracture propagation directions is less than a determined reference value. The fracture surface image analysis method according to any one of Technical Proposals 11 to 14.

[0079] (Technical Proposal 16) The first image is obtained from an imaging device that images the fracture plane, The second process includes deriving the fracture starting point position using common coordinates related to the plurality of fracture propagation directions, The coordinates are reference coordinates at the time of imaging by the imaging device, and the fracture plane image analysis method according to any one of Technical Proposals 11 to 15.

[0080] (Technical Proposal 17) Further perform at least any one of a first display operation, a second display operation, a third display operation, a fourth display operation, a fifth display operation, a sixth display operation, and a seventh display operation, In the first display operation, at least a part of the plurality of fracture propagation directions is displayed superimposed on the first image, In the second display operation, a part of the plurality of fracture propagation directions is selectively displayed according to the directions of the plurality of fracture propagation directions, In the third display operation, a part of the plurality of fracture propagation directions is displayed in units of the plurality of patch regions, In the fourth display operation, the plurality of fracture propagation directions related to the whole of the first image are displayed, In the fifth display operation, an averaged fracture propagation direction is displayed, and the averaged fracture propagation direction is obtained by averaging at least a part of the plurality of fracture propagation directions, In the sixth display operation, the plurality of patch regions are displayed in an image coordinate system, In the seventh display operation, the fracture starting point position is displayed, and the fracture plane image analysis method according to Technical Proposal 13 or 14.

[0081] (Technical Proposal 18) Further perform at least any one of an eighth display operation and a ninth display operation, In the eighth display operation, a part of the plurality of fracture propagation directions is selectively displayed based on the confidence level related to each of the plurality of fracture propagation directions, In the ninth display operation, a part of the plurality of fracture propagation directions used when deriving the fracture starting point position is selectively displayed, and the fracture plane image analysis method according to any one of Technical Proposals 11 to 14.

[0082] (Technical Solution 19) The plurality of fracture propagation directions include a first direction, a second direction, and a third direction, The first direction is the direction from a first starting point to a first ending point, The second direction is the direction from a second starting point to a second ending point, The third direction is the direction from a third starting point to a third ending point, The position of the second ending point on the straight line along the first direction is between the position of the second starting point on the straight line and the position of the first ending point on the straight line, The position of the first starting point on the straight line is between the position of the second ending point on the straight line and the position of the first ending point on the straight line, The second process includes repeatedly performing a starting point derivation process, One of the starting point derivation processes includes determining the second direction based on the first direction, The third direction corresponds to the second direction specified by repeated execution of the starting point derivation process, The second process is a fracture surface image analysis method according to any one of Technical Solutions 11 to 18, which uses the position of the extension line in the direction from the third ending point to the third starting point as a candidate for the fracture starting point position.

[0083] (Technical Solution 20) The first process includes a process by a regression processing unit configured to perform a process based on machine learning related to a plurality of teacher images including the fracture surface and the plurality of fracture propagation directions, according to any one of Technical Solutions 11 to 19.

[0084] According to the embodiment, a fracture surface image analysis apparatus and a fracture surface image analysis method capable of high-precision analysis can be provided.

[0085] The embodiments of the present invention have been described above with reference to specific examples. However, the present invention is not limited to these specific examples. For example, regarding the specific configurations of each element such as the acquisition unit and the processing unit included in the cross-sectional image analysis device, those skilled in the art can appropriately select from the known range to similarly implement the present invention and obtain the same effects as long as they are included in the scope of the present invention.

[0086] In addition, combinations of any two or more elements of each specific example within the technically possible range are also included in the scope of the present invention as long as they include the gist of the present invention.

[0087] Furthermore, based on the cross-sectional image analysis device and the cross-sectional image analysis method described above as embodiments of the present invention, all cross-sectional image analysis devices and cross-sectional image analysis methods that those skilled in the art can appropriately design and modify and implement also belong to the scope of the present invention as long as they include the gist of the present invention.

[0088] In addition, within the scope of the idea of the present invention, those skilled in the art can conceive of various modification examples and correction examples, and it is understood that those modification examples and correction examples also belong to the scope of the present invention.

[0089] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0090] 50: Imaging device, 70: Processing unit, 70C: Reference coordinate, 70a, 70b: First and second processing parts, 71: Divider, 71D: First image, 71P: Patch area, 72: Model selector, 72A, 72B: First and second models, 72M: Model, 72a: Destruction mode, 72b: Material, 72c: Shape, 72d: Forming conditions, 74: Patch extractor, 75: Acquisition unit, 79a: GUI, 79b: Display, 79c: Input unit, 79d: Storage, 81: Member, 110: Fracture surface image analysis device, 210: Analysis device, Ar1, Ar2, As1: Vectors, CN1: Confidence level, D1~D3: First to third directions, Dr1: Fracture propagation direction, Dr2: Fracture propagation direction after extraction, Dra1: Averaged fracture propagation direction, E1~E3: First to third end points, Ln1: Straight line, Ln2: Extension line, S1~S3: First to third starting points, SP1: Fracture starting point position, SPL1~SPL3: First to third samples

Claims

1. An acquisition unit configured to acquire a first image including a fracture surface of a member; A processing unit configured to perform image analysis on the first image; Comprising; The image analysis includes a first process and a second process, The first process includes deriving a plurality of fracture propagation directions in the fracture surface, One of the plurality of fracture propagation directions corresponds to one of a plurality of positions included in the fracture surface, The second process includes deriving a fracture initiation position in the fracture surface based on at least a part of the plurality of fracture propagation directions, a fracture surface image analysis device.

2. The processing unit includes a plurality of models, In a first operation, the processing unit performs the first process using one of the plurality of models, In a second operation, the processing unit performs the first process using another one of the plurality of models, At least one of the fracture mode of the fracture surface, the material of the member, the shape of the member, and the molding conditions of the member is different between the one of the plurality of models and the another one of the plurality of models, The fracture surface image analysis device according to claim 1.

3. The first process includes deriving one of the plurality of fracture propagation directions with respect to one of a plurality of patch regions obtained by dividing the first image acquired by the acquisition unit, The fracture surface image analysis device according to claim 1.

4. The first process includes changing a range included in at least one of the plurality of patch regions according to a magnification of imaging of the first image, The fracture surface image analysis device according to claim 3.

5. The first process further includes deriving a confidence level for each of the derived plurality of fracture propagation directions, The second process includes deriving the fracture initiation position without using at least one of the plurality of fracture propagation directions, and the confidence level corresponding to the at least one of the plurality of fracture propagation directions is less than a determined reference value, The fracture surface image analysis device according to any one of claims 1 to 4.

6. The first image is obtained from an imaging device that images the fracture surface, The second process includes deriving the fracture initiation position using a common coordinate regarding the plurality of fracture propagation directions, The coordinate is a reference coordinate at the time of imaging of the imaging device, The fracture surface image analysis device according to claim 1.

7. Further comprising a GUI The GUI is configured to perform at least one of a first display operation, a second display operation, a third display operation, a fourth display operation, a fifth display operation, a sixth display operation, and a seventh display operation. In the first display operation, the GUI overlays and displays at least a part of the plurality of fracture propagation directions on the first image. In the second display operation, the GUI selectively displays a part of the plurality of fracture propagation directions according to the directions of the plurality of fracture propagation directions. In the third display operation, the GUI displays a part of the plurality of fracture propagation directions in units of the plurality of patch regions. In the fourth display operation, the GUI displays the plurality of fracture propagation directions related to the whole of the first image. In the fifth display operation, the GUI displays an averaged fracture propagation direction, and the averaged fracture propagation direction is obtained by averaging at least a part of the plurality of fracture propagation directions. In the sixth display operation, the GUI displays the plurality of patch regions in an image coordinate system. In the seventh display operation, the GUI displays the fracture starting point position, and the cross-sectional image analysis device according to claim 3 or 4.

8. Further comprising a GUI, The GUI is configured to perform at least one of an eighth display operation and a ninth display operation. In the eighth display operation, the GUI selectively displays a part of the plurality of fracture propagation directions based on the confidence levels related to each of the plurality of fracture propagation directions. In the ninth display operation, the GUI selectively displays the part of the plurality of fracture propagation directions used when deriving the fracture starting point position, and the cross-sectional image analysis device according to claim 1.

9. Obtain a first image including a cross-section of a member, Execute image analysis on the first image by a processing unit, The image analysis includes a first process and a second process, The first process includes deriving a plurality of fracture propagation directions in the cross-section, One of the plurality of fracture propagation directions corresponds to one of the plurality of positions included in the cross-section, The second process includes deriving a fracture starting point position in the cross-section based on at least a part of the plurality of fracture propagation directions, and a cross-sectional image analysis method.

10. The processing unit includes a plurality of models, In the first operation, the processing unit performs the first process using one of the plurality of models. In the second operation, the processing unit performs the first processing using another one of the plurality of models. The fracture surface image analysis method according to claim 9, wherein at least one of the fracture mode of the fracture surface, the material of the member, the shape of the member, and the molding conditions of the member is different between the one of the plurality of models and the another one of the plurality of models.

Images