Judging System
The determination system addresses the challenge of assessing flange sealing surface conditions by using image analysis and color difference evaluation to provide maintenance advice, ensuring effective gas leak prevention.
Patent Information
- Application Number
- JP2021055691
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-03-29
- Publication Date
- 2024-11-27
- Estimated Expiration
- 2041-03-29
AI Technical Summary
Existing gas leak detection systems require technical knowledge and experience to assess the condition of flange sealing surfaces, making it difficult for unskilled personnel to determine the appropriate maintenance actions for gaskets.
A determination system that uses image acquisition and color difference analysis to evaluate the condition of flange sealing surfaces, determining the presence of rust and scratches, and provides advice on necessary maintenance actions.
Enables quick and efficient assessment of flange sealing surface conditions, allowing non-experts to take appropriate maintenance measures, thereby reducing the risk of gas leaks.
Smart Images

Figure 0007590901000001 
Figure 0007590901000002 
Figure 0007590901000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a determination system. [Background technology]
[0002] Conventionally, there are gas leak detection systems for finding high-temperature leaks that occur in the flanges of piping that transport fluids. For example, Japanese Patent Application Laid-Open No. 2009-192470 (Patent Document 1) discloses a technology that uses an infrared camera to remotely detect gas leaks from piping flanges even when the amount of leakage is small. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2009-192470 A Summary of the Invention [Problem to be solved by the invention]
[0004] One of the causes of gas leakage from flanges is deterioration or damage of gaskets used at pipe joints, so workers regularly replace the gaskets. At this time, workers visually check the condition of the flange's sealing surface, and depending on the condition, perform appropriate work such as cleaning or polishing the flange's sealing surface, and then replace it with a new gasket. However, technical knowledge and experience are required to check the condition of the flange's sealing surface and perform appropriate work corresponding to it. Therefore, even if an unskilled person with little knowledge or experience checks the sealing surface, it is often difficult to immediately determine what work should be performed. Therefore, a system that can easily determine the condition of the flange's sealing surface without relying on individual knowledge or experience is needed.
[0005] An object in one aspect of the present disclosure is to provide a determination system that can easily determine the condition of a sealing surface of a flange. [Means for solving the problem]
[0006] A judgment system according to one embodiment includes an image acquisition unit that acquires an image of the seal surface of a target flange; a color difference calculation unit that calculates a first color difference between a color value of a first image of a first seal surface having rust and a color value of the image of the seal surface of the target flange and a second color difference between a color value of a second image of a second seal surface having no adhesion and a color value of the image of the seal surface of the target flange; a consistency calculation unit that calculates a first degree of agreement between the first seal surface and the seal surface of the target flange based on the first color difference and calculates a second degree of agreement between the second seal surface and the seal surface of the target flange based on the second color difference; and a first judgment unit that judges the adhesion state of adhesion matter on the seal surface of the target flange based on the first degree of agreement and the second degree of agreement.
[0007] Preferably, when the first degree of coincidence is equal to or greater than a first threshold value, the first determination unit determines that rust is present on the sealing surface of the target flange, regardless of the second degree of coincidence.
[0008] Preferably, when the first degree of coincidence is less than a second threshold value that is smaller than the first threshold value and the second degree of coincidence is equal to or greater than a third threshold value, the first judgment unit judges that no adhesion is present on the sealing surface of the target flange.
[0009] Preferably, when the first degree of match is less than the second threshold value and the second degree of match is less than the third threshold value, the first judgment unit judges that an attachment other than rust is attached to the sealing surface of the target flange.
[0010] Preferably, the judgment system further includes a detection unit that detects scratches that have occurred on the sealing surface of the target flange based on an image of the sealing surface of the target flange, an area judgment unit that judges whether the scratch is included in a first area close to the center of the sealing surface of the target flange or a second area far from the center, and a second judgment unit that judges whether the scratch is acceptable or not based on at least one of the thickness, length, and angle of the scratch and the area in which the scratch exists.
[0011] Preferably, when the scratch is present in the first region and the thickness of the scratch is equal to or larger than a reference value or the angle of the scratch is equal to or larger than a predetermined angle, the second determination unit determines that the scratch is not acceptable.
[0012] Preferably, when the scratch is present in the second region, the thickness of the scratch is equal to or greater than a reference value, and the angle of the scratch is equal to or greater than a predetermined angle, the second determination unit determines that the scratch is unacceptable.
[0013] Preferably, when the scratch is present in the second region, the thickness of the scratch is less than a reference value, the angle of the scratch is less than a predetermined angle, and the length of the scratch is less than a predetermined length, the second judgment unit judges that the scratch is acceptable.
[0014] Preferably, the determination system further includes an output control unit which outputs advice information regarding the target flange based on at least one of the determination result of the first determination unit and the determination result of the second determination unit.
[0015] Preferably, the output control unit outputs advice information recommending polishing of the sealing surface of the target flange based on a judgment result of the first judgment unit that rust is attached to the sealing surface of the target flange, or a judgment result of the second judgment unit that the detected scratches are not acceptable. Effect of the Invention
[0016] According to the present disclosure, it becomes possible to easily determine the condition of the sealing surface of the flange. [Brief description of the drawings]
[0017] [Figure 1] FIG. 1 is a diagram for explaining an overall configuration of a determination system. [Diagram 2] 1 is a flowchart illustrating an example of an outline of an operation of the determination system. [Diagram 3] FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing device. [Figure 4] FIG. 13 is a diagram for explaining an analysis region of a seal surface of a flange. [Diagram 5]FIG. 5 is a diagram for explaining details of the analysis region in FIG. 4. [Figure 6] FIG. 13 is a diagram for explaining criteria for determining an adhesion state. [Figure 7] 7 is a diagram for explaining the results of judging the attachment state of each flange according to the judging criteria of FIG. 6. FIG. [Figure 8] 11A and 11B are diagrams for explaining a method of determining an adhesion state and advice information. [Figure 9] 13 is a diagram for explaining details of an analysis region used to determine the state of damage to a sealing surface. FIG. [Figure 10] 10A and 10B are diagrams for explaining a method for detecting damage occurring on a sealing surface. [Figure 11] 11 is a diagram for explaining a method for determining the state of damage to the sealing surface. FIG. [Figure 12] FIG. 13 is a diagram showing an example of a display of a result report. [Figure 13] FIG. 2 is a block diagram showing an example of a functional configuration of an information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] Hereinafter, the present embodiment will be described with reference to the drawings. In the following description, the same components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.
[0019] <System configuration> FIG. 1 is a diagram for explaining the overall configuration of a determination system 1000. Referring to FIG. 1, the determination system 1000 is a system for determining the state of a sealing surface of a flange 24. The determination system 1000 includes an information processing device 10, a camera 22, a server 30, and a terminal device 40. In this embodiment, it is assumed that the information processing device 10 determines the state of the sealing surface of the flange 24 when an operator who is a user of the terminal device 40 replaces a used sealing material that has been used to fasten the flange 24 with a new unused sealing material. Hereinafter, the sealing surface of the flange 24 to be determined may be referred to as a "target sealing surface."
[0020] A sealing material that matches the specifications of the flanges 24 is used. In order to properly fasten the pair of flanges 24 via the sealing material, the worker captures an image of the target seal surface using the camera 22 and imports the captured image into the terminal device 40. The terminal device 40 transmits the captured image to the information processing device 10. The information processing device 10 analyzes the received captured image to determine the condition of the target seal surface, and transmits advice information based on the determination result to the terminal device 40.
[0021] The sealing material is sandwiched between the joints of the pair of flanges 24 and fixed by tightening the bolts of the flanges 24, thereby preventing fluid from leaking from the gaps of the flanges 24. The sealing material is, for example, a fixed sealing material called a gasket. The gasket is a sealing material that can seal the gaps in the area where it is installed and provide airtightness to the area. There are various types of gaskets, and an appropriate gasket is selected according to the usage mode of the piping. The sealing material may be a dynamic sealing material called a packing.
[0022] The terminal device 40 is configured to be able to communicate with the information processing device 10. The terminal device 40 acquires a captured image of the flange 24 and transmits the captured image to the information processing device 10. In response to the captured image, the terminal device 40 receives advice information on the state of the target seal surface from the information processing device 10. The terminal device 40 is typically a smartphone, but is not limited to this and may be, for example, a tablet terminal device. The terminal device 40 may be configured to be able to communicate with the server 30.
[0023] The terminal device 40 acquires a captured image of the sealing surface of the flange 24 from the camera 22. The camera 22 includes, for example, an imaging element partitioned into a plurality of pixels, such as a CCD (Coupled Charged Device) or a CMOS (Complementary Metal Oxide Semiconductor) sensor, in addition to an optical system such as a lens. The captured image acquired by the camera 22 is transmitted to the terminal device 40.
[0024] In this embodiment, the information processing device 10 judges the state of the target seal surface based on a captured image of the flange 24 to be judged and captured images of flanges in various states stored in a database.
[0025] The information processing device 10 typically has a structure conforming to a general-purpose computer architecture, and realizes various processes described below by a processor executing a program installed in advance. The information processing device 10 is, for example, a desktop PC (Personal Computer). However, the information processing device 10 may be any other device (for example, a laptop PC, a tablet terminal device) as long as it is capable of executing the functions and processes described below.
[0026] The server 30 is configured to be able to communicate with the information processing device 10. The server 30 receives various processing results from the information processing device 10, and stores these in a database.
[0027] Fig. 2 is a flow chart for explaining an example of an outline of the operation of the determination system. Referring to Fig. 2, the camera 22 captures an image of the sealing surface of the flange 24 to generate a captured image (step S10). The information processing device 10 acquires the captured image from the camera 22 and stores it in an internal memory (step S12). The information processing device 10 also stores the imaging conditions (e.g., imaging distance, resolution, light irradiation angle, light source wavelength, brightness, etc.) when the flange 24 was imaged.
[0028] The information processing device 10 calculates the color difference between the color value of the image of the seal surface of the flange 24 and the color values of the images of the multiple reference seal surfaces (step S14). For example, when the color value of the image of the target seal surface is L1 * ,a1 * ,b1 * and the color value of the image of the reference seal surface is L2 * ,a2 * ,b2 * In this case, the color difference ΔE is ΔE={(L2 * -L1 * ) 2 +(a2 * -a1 * ) 2 +(b2 * -b1 * ) 2} 1 / 2 The color values of the multiple reference seal surfaces include, for example, color values of a seal surface with rust and color values of a seal surface in good condition with no adhesion. The color values of the images of the respective reference seal surfaces (or the images themselves) are stored in the memory of the information processing device 10.
[0029] The information processing device 10 executes a judgment process using the calculated color differences ΔE to execute a process for judging the adhesion state of the adhesion matter on the target seal surface (step S16). Although details will be described later, the information processing device 10 calculates the degree of coincidence between each reference seal surface and the target seal surface using each color difference ΔE, and judges the adhesion state of the target seal surface based on each degree of coincidence. The information processing device 10 analyzes a binarized image obtained by binarizing the captured image to detect a scratch that has occurred on the target seal surface (step S18). The information processing device 10 executes a process for judging the state of the detected scratch (step S20). Although details will be described later, the information processing device 10 judges whether or not the detected scratch is acceptable (i.e., whether or not the scratch is within an acceptable range) based on the position, thickness, angle, length, etc. of the detected scratch.
[0030] The information processing device 10 generates advice information based on each of the judgment results performed in steps S16 and S20, and transmits each of the judgment results and the advice information to the terminal device 40 (step S22). The terminal device 40 displays each of the received judgment results and advice information on a display (step S24). The information processing device 10 may transmit each of the judgment results and advice information to the server 30. In this case, the server 30 stores the judgment results and advice information received from the information processing device 10 in a database.
[0031] The determination system 1000 uses a captured image of the seal surface of the flange 24 to determine the state of adhesion of the deposits and the state of scratches on the seal surface, and provides advice information according to the state. Therefore, even an unskilled person can quickly grasp the state of the seal surface, and can efficiently take measures appropriate to the state of the seal surface.
[0032] <Hardware configuration> (Information processing device) Fig. 3 is a block diagram showing an example of a hardware configuration of the information processing device 10. With reference to Fig. 3, the information processing device 10 includes a processor 101, a memory 103, a display 105, an input device 107, an input / output interface (I / F) 109, and a communication interface (I / F) 111. These components are connected to each other so as to be able to communicate data with each other.
[0033] The processor 101 is typically an arithmetic processing unit such as a CPU (Central Processing Unit), an MPU (Multi Processing Unit), etc. The processor 101 controls the operation of each unit of the information processing device 10 by reading and executing a program stored in the memory 103. More specifically, the processor 101 realizes each function of the information processing device 10 by executing the program.
[0034] The memory 103 is realized by a random access memory (RAM), a read-only memory (ROM), a flash memory, a hard disk, etc. The memory 103 stores a program executed by the processor 101, captured images acquired by the camera 22, etc.
[0035] The display 105 is, for example, a liquid crystal display, an organic EL (Electro Luminescence) display, etc. The display 105 may be configured integrally with the information processing device 10, or may be configured separately from the information processing device 10.
[0036] The input device 107 accepts operation inputs to the information processing device 10. The input device 107 is realized by, for example, a keyboard, a button, a mouse, etc. Furthermore, the input device 107 may be realized as a touch panel.
[0037] The input / output interface 109 mediates data transmission between the processor 101 and the camera 22. The input / output interface 109 is connected to, for example, the camera 22. The processor 101 acquires an image captured by the camera 22 via the input / output interface 109.
[0038] The communication interface 111 mediates data transmission between the processor 101 and the server 30, the terminal device 40, etc. As a communication method, for example, a wireless communication method such as Bluetooth (registered trademark) or a wireless LAN (Local Area Network) is used. Note that a wired communication method such as a USB (Universal Serial Bus) may also be used as the communication method. Note that the processor 101 may communicate with the camera 22 via the communication interface 111.
[0039] (server) The server 30 may have a known hardware configuration as long as it can provide information processing as described below as a whole. For example, the server 30 may include a processor for executing various processes, a memory for storing programs and data, a communication interface for transmitting various data to and from the information processing device 10, and an input device for receiving instructions from a user.
[0040] (Terminal Device) The terminal device 40 may have a known hardware configuration as long as it can provide information processing as described below as a whole. For example, the terminal device 40 includes a processor, a memory, a communication interface for transmitting and receiving various data to and from the information processing device 10, a touch panel for receiving instructions from a user, and a display for displaying various information.
[0041] <Method of determining adhesion state> FIG. 4 is a diagram for explaining the analysis area of the seal surface of the flange 24. Referring to FIG. 4, the analysis areas 51 to 58 of the flange 24 are set in an area including the fastening portion 61 in the seal surface of the flange 24. The fastening portion 61 is a portion where a seal material (for example, a gasket) is disposed. The camera 22 captures an image of the seal surface of the flange 24 so as to include the analysis areas 51 to 58. The camera 22 may generate a captured image including all of the analysis areas 51 to 58, or may generate a different captured image for each of the analysis areas 51 to 58. The information processing device 10 executes a process of determining the adhesion state for each of the analysis areas 51 to 58. The method of determining the adhesion state in each analysis area is the same. Therefore, hereinafter, the method of determining the adhesion state in the analysis area 51 will be described as a representative example.
[0042] Fig. 5 is a diagram for explaining details of the analysis region in Fig. 4. Specifically, Fig. 5(a) is a schematic cross-sectional view taken along line VV shown in Fig. 4. Fig. 5(b) is a diagram showing an image including the analysis region 51 in Fig. 4.
[0043] Referring to Fig. 5(a), C is the center circle diameter of the bolt hole, D is the outer diameter, g is the seat diameter, d is the inner diameter, and h is the bolt hole diameter. The distance between point P1 and point P2 in the rectangular analysis region 51 of Fig. 5(b) is denoted as LP. In this case, LP = (C / 2 - d / 2 - h / 2).
[0044] Also, let the distance between point Q1 and point Q2 in the analysis region 51 of Fig. 5(b) be LQ. As shown in Fig. 4, the number of bolts is 8, and LQ corresponds to the length of one side of the octagon. Therefore, LQ = 2(C / 2 - h / 2) × tan{(360° / (2×8)}. The analysis region 51 has four regions 51A to 51D divided by the line segment connecting point P1 and point P2 and the line segment connecting point Q1 and point Q2.
[0045] Fig. 6 is a diagram for explaining the adhesion state determination criteria. Specifically, Fig. 6(a) is a diagram showing the relationship between the color difference consistency M and the points. When 80 < M ≤ 100, the rank is R4 and the point is 80. When 60 < M ≤ 80, the rank is R3 and the point is 60. When 20 < M ≤ 60, the rank is R2 and the point is 20. When M ≤ 20, the rank is R1 and the point is 0.
[0046] Fig. 6(b) is a diagram showing the relationship between the average point of the consistency M1 in each region 51A to 51D and the rust level indicating the degree of rust adhesion. When the average point is 50 or more, the rust level is "3". The rust level "3" indicates that rust has adhered to the seal surface. When the average point is more than 10 and less than 50, the rust level is "2". The rust level "2" indicates that rust and deposits other than rust have adhered to the seal surface. When the average point is less than 10, the rust level is "1". The rust level "1" indicates that deposits other than rust have adhered to the seal surface or there are no deposits. The average point of the consistency M1 in each region 51A to 51D corresponds to the consistency M1 in the analysis region 51.
[0047] FIG. 6(c) is a diagram showing the relationship between the average score of the degree of coincidence M2 in each of the regions 51A to 51D and the quality level indicating how good the condition is. When the average score is 50 or more, the quality level is "3". The quality level "3" indicates a clean condition with almost no adhesion on the sealing surface. When the average score is 10 or more and less than 50, the quality level is "2". The quality level "2" indicates an average condition with some adhesion on the sealing surface. When the average score is less than 10, the quality level is "1". The quality level "1" indicates a dirty condition with adhesion on the sealing surface. The average score of the degree of coincidence M2 in each of the regions 51A to 51D corresponds to the degree of coincidence M2 in the analysis region 51.
[0048] Fig. 7 is a diagram for explaining the judgment result of the adhesion state of each flange according to the judgment criteria of Fig. 6. The information processing device 10 judges the state of the seal surface of the flanges Ka, Kb, Kc (hereinafter, also collectively referred to as "flange K"). The color values of each of the regions 51A-51D of the seal surface in a rusted state and the color values of each of the regions 51A-51D of the seal surface in a no-adhesion state are stored in the memory 103 of the information processing device 10.
[0049] The information processing device 10 evaluates the rust level of each of the regions 51A to 51D of the flange K. Specifically, the information processing device 10 calculates the color difference ΔE1 between the color value of the region 51A of the seal surface of the flange K and the color value of the region 51A of the seal surface to which rust has adhered. The information processing device 10 converts the color difference ΔE1 into a ratio to calculate the degree of agreement M1 expressed as a percentage. It is calculated as M1=(1 / ΔE1). For example, when ΔE1=2.8, M1=(1 / 2.8)×100=35.7%. The degree of agreement M1 is calculated similarly for the regions 51B to 51D.
[0050] 6 and 7, in flange Ka, the ranks of regions 51A, 51B, 51C, and 51D are R3, R3, R4, and R4, respectively. Furthermore, the average value of the points (i.e., the average point) of each of regions 51A to 51D is 70, so the rust level is "3" (see FIG. 6(b)). Similarly, in flange Kb, the average point is 5, so the rust level is "1." In flange Kc, the average point is 40, so the rust level is "2."
[0051] Next, the information processing device 10 evaluates the quality level of each of the regions 51A to 51D of the flange K. Specifically, the information processing device 10 calculates the color difference ΔE2 between the color value of the region 51A of the seal surface of the flange K and the color value of the region 51A of the seal surface where no attached matter is present. The information processing device 10 converts the color difference ΔE2 into a ratio to calculate the degree of agreement M2 expressed as a percentage. The calculation is M2=(1 / ΔE2). The degree of agreement M2 is similarly calculated for the regions 51B to 51D.
[0052] 6 and 7, for flange Ka, the rust level is "3" and it is determined that rust is present, so the evaluation of the pass level is omitted. Note that the evaluation of the pass level may also be performed for flange Ka. For flange Kb, the ranks of areas 51A, 51B, 51C, and 51D are R2, R2, R2, and R1, respectively. Also, the average value of the points (i.e., the average point) of each of areas 51A to 51D is 15, so the pass level is "2" (see FIG. 6(c)). Similarly, for flange Kc, the average point is 40, so the pass level is "2".
[0053] As a result, the information processing device 10 determines that there is rust on the sealing surface of the flange Ka, that there is some kind of attachment other than rust on the sealing surface of the flange Kb, and that there is rust and other attachment other than rust on the sealing surface of the flange Kc. The other attachment is, for example, a part of a sealing material (gasket).
[0054] Next, a more specific description will be given of a method for determining the adhesion state based on a combination of the rust level and the pass / fail level, and advice information provided according to the adhesion state.
[0055] 8 is a diagram for explaining a method of judging the adhesion state and advice information. With reference to FIG. 8, when the rust level is "1", or when the rust level is "2" and the non-defective level is "3", the information processing device 10 R The system determines that there is rust on the surface (corresponding to "rust" in Figure 8) and generates advice information recommending polishing the sealing surface.
[0056] If the rust level is "2" and the non-defective level is "2" or "1", the information processing device 10 R It determines that rust and other deposits are present on the surface (corresponding to "Rust / Deposition" in Figure 8) and generates advice information recommending polishing and cleaning of the sealing surface.
[0057] If the rust level is "1" and the non-defective level is "3", the information processing device 10 R It is determined that there is no adhesion on the surface and that the surface is in a good condition (corresponding to "good" in FIG. 8), and advice information indicating that the surface is in a good condition is generated. In this case, the information processing device 10 generates information that prompts the operator to determine the scratch condition.
[0058] If the rust level is "1" and the non-defective level is "2" or "1", the information processing device 10 R It is determined that there is something other than rust on the surface (corresponding to "adhesion" in Figure 8), and R Generate advice information recommending cleaning of the surface.
[0059] Typically, the worker R If you find advice that recommends polishing or cleaning the surface, RThe surface is imaged and the imaged image is transmitted to the information processing device 10. The information processing device 10 judges the adhesion state again based on the imaged image. In this case, if the information processing device 10 judges the adhesion state as "rust" or "rust / adhesion", it generates advice information recommending re-polishing. If the information processing device 10 judges the adhesion state as "adhesion", it generates advice information recommending polishing.
[0060] If the information processing device 10 judges the adhesion state to be "rust" or "rust / adhesion", it generates advice information recommending re-grinding. If the information processing device 10 judges the adhesion state to be "adhesion", it generates advice information recommending grinding. If the information processing device 10 judges as a result of the re-judgment that the adhesion state is good, it generates information that prompts the worker to judge the scratch state.
[0061] 6, the analysis area 51 is divided into four areas 51A to 51D, but may not be divided. Also, the information processing device 10 converts the degree of coincidence for each of the areas 51A to 51D into points and determines the adhesion state based on the average value of the points (i.e., the average point), but may not convert into points.
[0062] For example, when the degree of coincidence M1 in the analysis region 51 is equal to or greater than a threshold value Th1 (for example, 50%) (for example, rust level 3), the information processing device 10 determines that the seal of the flange 24 is rusted regardless of the degree of coincidence M2. R The information processing device 10 determines that rust is attached to the sealing surface of the flange 24. Also, if the degree of agreement M1 is less than a threshold Th2 (e.g., 10%) that is smaller than the threshold Th1 (e.g., rust level 1) and the degree of agreement M2 is equal to or greater than a threshold Th3 (e.g., 50%) (e.g., pass level 3), the information processing device 10 may determine that no attachment is present on the sealing surface of the flange 24 (i.e., good condition). Furthermore, if the degree of agreement M1 is less than the threshold Th2 (e.g., rust level 1) and the degree of agreement M2 is less than the threshold Th3 (e.g., pass level 2 or 1), the information processing device 10 determines that other attachment is attached to the sealing surface of the flange 24.
[0063] <Method of determining the condition of scratches> Figure 9 shows the R 9A and 9B are diagrams for explaining details of an analysis region used to determine the state of scratches on a surface. Specifically, Fig. 9A is a schematic cross-sectional view taken along line VV shown in Fig. 4. Fig. 9B is a diagram showing an image including the analysis region 51 of Fig. 4.
[0064] 9(a) and 9(b), the analysis area used to determine the state of damage to the sealing surface is a rectangular area 500 included in the analysis area 51. The distance between points P2 and P3, which is the vertical length of the rectangular area 500, is defined as LP1. In this case, LP1=(g / 2-d / 2). The distance between points Q3 and Q4, which is the horizontal length of the rectangular area 500 in FIG. 9(b), is defined as LQ1. LQ1 is the same as the distance LQ in FIG. 5. Therefore, LQ1=2(C / 2-h / 2)×tan{(360° / (2×8)}.
[0065] Figure 10 shows the R 10 is a diagram for explaining a method of detecting scratches on a surface. With reference to FIG. 10, in step J1, the information processing device 10 generates an image 81 by binarizing the rectangular area 500 in FIG. 9(b). In step J2, the information processing device 10 detects a line 71 indicating the inner circumference of the fastening portion 61 shown in FIG. 4 and a line 72 indicating the outer circumference of the fastening portion 61 by image processing. The information processing device 10 draws a line 73 that bisects the area surrounded by the lines 71 and 72, and divides the area surrounded by the lines 71 and 72 into an area Ai surrounded by the lines 71 and 73 and an area Ao surrounded by the lines 72 and 73.
[0066] In step J3, the information processing device 10 detects scratches occurring in the areas Ai and Ao, and draws a line segment 77 indicating the detected scratches. R For example, the information processing device 10 detects the defect by comparing the feature amount of the defect stored in advance in the memory 103 with the feature amount of the image in the area Ai and the area Ao. RThe information processing device 10 also calculates the width W of the line segment 77.
[0067] In step J4, the information processing device 10 calculates the length F of the line segment 77. For example, the information processing device 10 defines an xy plane with one end of the line segment 77 as the origin. In this case, if the coordinates of the other end of the line segment 77 are (x1, y1), then F=(x1 2 +y1 2 ) 1 / 2 In step J5, the information processing device 10 calculates the angle θ between the line segment 77 and the x-axis. Here, the angle θ is assumed to be an acute angle.
[0068] Figure 11 shows the R 11 is a diagram for explaining a method for determining the state of a scratch on a surface. Referring to Fig. 11, the information processing device 10 determines the state of the scratch based on the position of the detected scratch (line segment 77), the thickness W of the scratch, the length F of the scratch, and the angle θ.
[0069] Specifically, the information processing device 10 judges whether the detected damage is included in area Ai or area Ao. When the damage is included in both area Ai and area Ao, the information processing device 10 judges that the damage is included in area Ai. Area Ai is an area close to the center of the seal surface, and area Ao is an area far from the center of the seal surface. Therefore, area Ai is more inward than area Ao and closer to the location where the fluid (e.g., gas) is transported. Therefore, in consideration of fluid leakage, it is preferable that the damage is present in area Ao rather than area Ai.
[0070] The information processing device 10 judges whether the thickness W of the scratch is equal to or greater than a reference value Ra. The reference value Ra is, for example, the surface roughness at the time of flanging. This is based on the idea that if the thickness of the scratch is less than the surface roughness at the time of flanging, the thickness of the scratch is generally acceptable.
[0071] The information processing device 10 judges whether the length F is equal to or greater than a predetermined length. The predetermined length is, for example, ½ of the distance Dx (see FIG. 10) between the inner line 71 and the outer line 72 of the fastening portion 61. Since the longer the length F of the scratch, the more likely it is that fluid leakage will occur, it is preferable that the length F is smaller.
[0072] The information processing device 10 determines whether the angle θ is equal to or larger than a predetermined angle (for example, 45°). The larger the angle θ of the flaw, the more likely it is that fluid will leak from the inside to the outside, so a smaller angle θ is more preferable for the flaw.
[0073] The information processing device 10 judges the state of the detected scratch based on the above four judgment results. First, a case where the scratch is present in the area Ai will be described. When the thickness W is equal to or greater than the reference value Ra, or when the angle θ is equal to or greater than 45°, the information processing device 10 judges that the scratch is in a poor state. When the thickness W is less than the reference value Ra and the angle is less than 45°, the information processing device 10 judges that the scratch is in a slightly poor state.
[0074] Next, a case where the scratch exists in the area Ao will be described. When the thickness W is equal to or greater than the reference value Ra and the angle θ is equal to or greater than 45°, when the thickness W is equal to or greater than the reference value Ra and the length F is equal to or greater than Dx / 2, or when the thickness W is less than the reference value Ra and the angle θ is equal to or greater than 45° and the length F is equal to or greater than Dx / 2, the information processing device 10 determines that the scratch is in a poor state when the thickness W is equal to or greater than the reference value Ra and the angle θ is less than 45° and the length F is less than Dx / 2, when the thickness W is less than the reference value Ra and the angle θ is equal to or greater than 45° and the length F is less than Dx / 2, or when the thickness W is less than the reference value Ra and the angle θ is less than 45° and the length F is equal to or greater than Dx / 2, the information processing device 10 determines that the scratch is in a slightly poor state. When the thickness W is less than the reference value Ra and the angle θ is less than 45° and the length F is less than Dx / 2, the information processing device 10 determines that the scratch is in a good state.
[0075] When the state of the scratch is "bad" or "slightly bad", the information processing device 10 determines that the scratch is not acceptable (i.e., outside the acceptable range). Therefore, when the state of the scratch is "bad", the information processing device 10 R If the scratch condition is "slightly poor," the system generates advice that strongly recommends polishing the surface. R On the other hand, if the scratch condition is "good", the information processing device 10 determines that the scratch is tolerable (i.e., within the allowable range). Therefore, if the scratch condition is "good", the information processing device 10 does not recommend polishing the sheet. R Generate advice information indicating that the surface is available for use.
[0076] Typically, the worker R If you find advice that recommends polishing the surface, please do not reseal the product after completing the polishing work. R The surface is imaged and the imaged image is transmitted to the information processing device 10. The information processing device 10 judges the state of the scratch again based on the imaged image. If the information processing device 10 judges the state of the scratch as "slightly poor" in the previous judgment process and judges the state of the scratch as "slightly poor" in the current judgment process as well, it generates advice information to the effect that the flange 24 can be used, provided that the inspection frequency is increased.
[0077] If the information processing device 10 judged the scratch condition as "slightly poor" or "poor" in the previous judgment process and judged the scratch condition as "poor" in the current judgment process, it generates advice information recommending replacing the flange 24 with another flange. If the information processing device 10 judged the scratch condition as "slightly poor" or "poor" in the previous judgment process and judged the scratch condition as "good" in the current judgment process, it generates advice information to the effect that the flange 24 is usable.
[0078] In the flaw detection method shown in Fig. 10, RIf no scratches are detected on the surface, the information processing device 10 determines the scratch condition to be "good" and generates advice information to the effect that the flange 24 is usable.
[0079] <Display example> After performing the above-described process of determining the state of the flange 24, the information processing device 10 transmits the determination result and advice information to the terminal device 40. Based on the determination result and the advice information, the terminal device 40 displays a result report as shown in Fig. 12. Note that the information processing device 10 may transmit the determination result of the attachment state of the flange 24 and the determination result of the scratch state of the flange 24 separately or together.
[0080] 12 is a diagram showing an example of a display of a result report. Referring to Fig. 12, terminal device 40 displays a user interface screen 150 showing the result report on the display. User interface screen 150 includes display areas 152, 154, 156, 158, and 160.
[0081] The display area 152 is an area that displays an overview of the state of the flange 24. In the example of FIG. R 12, the surface is scratched and rust and other deposits are attached. Display area 154 is an area for displaying the improvement method. In the example of FIG. 12, the improvement method is to remove the seal of flange 24. R It is suggested that cleaning and polishing of the surface is recommended.
[0082] The display area 156 is an area for displaying details of the attachment state of the flange 24. In the example of FIG. R The result of the state judgment ("rust", "rust / attached" or "good") is shown for each of the eight points on the surface. The display area 158 is an area for displaying the details of the state of scratches on the flange 24. In the example of FIG. R The condition judgment result ("Scratched" or "Good") is shown for each of the eight points on the surface. Note that the condition judgment result "Scratched" corresponds to the judgment results of "Fairly Poor" or "Poor" in FIG. 11.
[0083] The display area 160 is an area that displays the implementation status of the state judgment of the flange 24. In the example of Fig. 12, the judgment of the adhesion state and the scratch state have been performed, and the judgment result of the adhesion state is shown as "rust / attached" and the judgment result of the scratch state is shown as "scratched". Then, the final judgment result shows that improvement is necessary.
[0084] <Functional configuration> Fig. 13 is a block diagram showing an example of a functional configuration of the information processing device 10. Referring to Fig. 13, the information processing device 10 includes, as main functional components, an image acquisition unit 201, a color difference calculation unit 203, a coincidence calculation unit 205, a first determination unit 207, a detection unit 209, a region determination unit 211, a second determination unit 213, and an output control unit 215. Each of these functions is realized, for example, by the processor 101 of the information processing device 10 executing a program stored in the memory 103. Note that some or all of these functions may be configured to be realized by hardware.
[0085] The image acquisition unit 201 acquires from the camera 22 a captured image of the sealing surface of the flange 24 captured by the camera 22 .
[0086] The color difference calculation unit 203 calculates a color difference (e.g., ΔE1) between a color value of the reference image of the first seal surface having rust and a color value of the image of the seal surface of the flange 24. The color difference calculation unit 203 calculates a color difference (e.g., ΔE2) between a color value of the reference image of the second seal surface having no adhesion and a color value of the image of the seal surface of the flange 24. The memory 103 stores the color values of the reference image of the seal surface having rust and the reference image of the seal surface having no adhesion.
[0087] The coincidence calculation unit 205 calculates, based on the color difference ΔE1, a coincidence M1 between the first seal surface and the seal surface of the flange 24. The coincidence calculation unit 205 calculates, based on the color difference ΔE2, a coincidence M2 between the second seal surface and the seal surface of the flange 24.
[0088] The first determination unit 207 determines the adhesion state of the deposit on the seal surface of the flange 24 based on the degree of agreement M1 and the degree of agreement M2. Specifically, when the degree of agreement M1 is equal to or greater than a threshold value Th1 (for example, 50%), the first determination unit 207 determines the adhesion state of the deposit on the seal surface of the flange 24 regardless of the degree of agreement M2. R If the degree of agreement M1 is less than a threshold value Th2 (e.g., 10%) and the degree of agreement M2 is equal to or greater than a threshold value Th3 (e.g., 50%), the first determination unit 207 determines that no attachment exists on the sealing surface of the flange 24. If the degree of agreement M1 is less than the threshold value Th2 and the degree of agreement M2 is less than the threshold value Th3, the first determination unit 207 determines that an attachment other than rust (e.g., a part of a sealing material) exists on the sealing surface of the flange 24.
[0089] The detection unit 209 detects scratches on the seal surface based on the image of the seal surface of the flange 24. The detection unit 209 detects the scratches according to the detection method described in Fig. 10. The detection unit 209 calculates the thickness W, length F, and angle θ of the scratches.
[0090] The area determination unit 211 determines whether the detected flaw is included in a first area (eg, area Ai) close to the center of the sealing surface of the flange 24, or in a second area (eg, area Ao) far from the center.
[0091] The second judgment unit 213 judges whether or not to accept the scratch based on at least one of the thickness W, length F, and angle θ of the scratch and the area in which the scratch exists. Specifically, if the scratch exists in the area Ai and the thickness W is equal to or greater than the reference value Ra or the angle θ is equal to or greater than a predetermined angle (for example, 45°), the second judgment unit 213 judges that the scratch is not acceptable. If the scratch exists in the area Ao and the thickness W is equal to or greater than the reference value Ra and the angle θ is equal to or greater than a predetermined angle, the second judgment unit 213 judges that the scratch is not acceptable. On the other hand, if the scratch exists in the area Ao and the thickness W is less than the reference value Ra, the angle θ is less than the predetermined angle, and the length F is less than the predetermined length, the second judgment unit 213 judges that the scratch is acceptable.
[0092] The output control unit 215 outputs advice information regarding the flange 24 based on at least one of the judgment result of the first judgment unit 207 and the judgment result of the second judgment unit 213. For example, the output control unit 215 outputs advice information recommending polishing of the sealing surface of the flange 24 based on the judgment result of the first judgment unit 207 that rust is attached to the sealing surface of the flange 24, or the judgment result of the second judgment unit 213 that the detected scratches are not acceptable.
[0093] <Advantages> According to this embodiment, the image of the seal surface of the flange is used to determine the state of adhesion of the deposits and the state of damage on the seal surface, and advice information according to the state is provided. Therefore, even an unskilled person can quickly grasp the state of the seal surface and can efficiently take measures appropriate to the state of the seal surface.
[0094] <Other embodiments> (1) The server 30 may have a part of the functional configuration of the information processing device 10 in Fig. 13 in the above-mentioned embodiment. For example, the information processing device 10 may have the image acquisition unit 201 and the color difference calculation unit 203, and the server 30 may have the coincidence calculation unit 205, the first determination unit 207, the detection unit 209, the area determination unit 211, the second determination unit 213, and the output control unit 215. In this case, the information processing device 10 transmits the color difference calculated by the color difference calculation unit 203 to the server 30.
[0095] (2) In the above-described embodiment, a program for causing a computer to function and execute the control as described in the above-described flowchart can also be provided. Such a program can be provided as a program product by being recorded on a non-transitory computer-readable recording medium such as a flexible disk, a CD-ROM (Compact Disk Read Only Memory), a secondary storage device, a main storage device, or a memory card that is attached to the computer. Alternatively, the program can be provided by being recorded on a recording medium such as a hard disk built into the computer. The program can also be provided by downloading via a network.
[0096] The program may be one that executes processing by calling necessary modules in a predetermined sequence at a predetermined timing among program modules provided as part of a computer's operating system (OS). In that case, the program itself does not include the above modules and executes processing in cooperation with the OS. Such a program that does not include a module may also be included in the program according to the present embodiment. Furthermore, the program according to the present embodiment may be one that is provided by being incorporated into a part of another program. In that case, the program itself does not include modules included in the other program, and executes processing in cooperation with the other program. Such a program incorporated into another program may also be included in the program according to the present embodiment.
[0097] (3) The configurations exemplified as the above-mentioned embodiments are merely examples of the configurations of the present invention, and may be combined with other known technologies, or may be modified, such as by omitting some parts, without departing from the scope of the present invention. In addition, the above-mentioned embodiments may be implemented by appropriately adopting the processes and configurations described in other embodiments.
[0098] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is defined by the claims, not the above description, and is intended to include all modifications within the scope and meaning equivalent to the claims. [Explanation of symbols]
[0099] 10 information processing device, 22 camera, 24 flange, 30 server, 40 terminal device, 61 fastening section, 101 processor, 103 memory, 105 display, 107 input device, 109 input / output interface, 111 communication interface, 150 user interface screen, 201 image acquisition section, 203 color difference calculation section, 205 matching degree calculation section, 207 first judgment section, 209 detection section, 211 area judgment section, 213 second judgment section, 215 output control section, 1000 judgment system.
Claims
1. an image acquisition unit for acquiring an image of a seal surface of a target flange; a color difference calculation unit that calculates a first color difference between a color value of a first image of a first seal surface having rust and a color value of an image of the seal surface of the target flange, and a second color difference between a color value of a second image of a second seal surface having no adhesion and a color value of the image of the seal surface of the target flange; a coincidence calculation unit that calculates a first coincidence between the first seal surface and the seal surface of the target flange based on the first color difference, and calculates a second coincidence between the second seal surface and the seal surface of the target flange based on the second color difference; a first determination unit that determines an adhesion state of adhesion matter on the seal surface of the target flange based on the first degree of coincidence and the second degree of coincidence.
2. The judgment system according to claim 1 , wherein when the first degree of coincidence is equal to or greater than a first threshold value, the first judgment unit judges that rust is present on the sealing surface of the target flange regardless of the second degree of coincidence.
3. The judgment system of claim 2, wherein when the first degree of coincidence is less than a second threshold value that is smaller than the first threshold value and the second degree of coincidence is equal to or greater than a third threshold value, the first judgment unit judges that no adhesion is present on the sealing surface of the target flange.
4. The judgment system described in claim 3, wherein when the first degree of coincidence is less than the second threshold value and the second degree of coincidence is less than the third threshold value, the first judgment unit judges that other attachments besides rust are attached to the sealing surface of the target flange.
5. a detection unit that detects damage to the seal surface of the target flange based on an image of the seal surface; an area determination unit that determines whether the flaw is included in a first area close to the center of the seal surface of the target flange or a second area far from the center; The judgment system according to any one of claims 1 to 4, further comprising a second judgment unit that judges whether or not to accept the scratch based on at least one of the thickness, length, and angle of the scratch and the area in which the scratch exists.
6. The judgment system according to claim 5 , wherein when the scratch is present in the first area and the thickness of the scratch is equal to or greater than a reference value or the angle of the scratch is equal to or greater than a predetermined angle, the second judgment unit judges that the scratch is not acceptable.
7. The judgment system according to claim 5 or 6, wherein when the scratch is present in the second area, the thickness of the scratch is equal to or greater than a reference value, and the angle of the scratch is equal to or greater than a predetermined angle, the second judgment unit judges that the scratch is not acceptable.
8. The judgment system according to any one of claims 5 to 7, wherein the second judgment unit judges that the scratch is acceptable when the scratch is present in the second area, the thickness of the scratch is less than a reference value, the angle of the scratch is less than a predetermined angle, and the length of the scratch is less than a predetermined length.
9. The judgment system according to any one of claims 5 to 8, further comprising an output control unit that outputs advice information regarding the target flange based on at least one of the judgment result of the first judgment unit and the judgment result of the second judgment unit.
10. The judgment system described in claim 9, wherein the output control unit outputs advice information recommending polishing of the sealing surface of the target flange based on a judgment result of the first judgment unit that rust is attached to the sealing surface of the target flange, or a judgment result of the second judgment unit that the detected scratch is not acceptable.
Citation Information
Patent Citations
Method for detecting defects of bearing sealing element based on vision
CN106404793A
Automatic flange surface inspector
JP1988122938A
Corrosion evaluation method for iron structure
JP2008128960A
Attachment for flange, gas leak detection system, and computer program
JP2009192470A
Optical coin identification device, coin processing machine, and coin identification method
JP2020064505A
