Measurement device, measurement method, and program

Abstract

A measurement device 10 comprises: an image information input unit 11 that receives input of a first image of a pipe cross-section captured by an SEM; a measurement reference line drawing unit 12 that creates a second image in which a circle, serving as a measurement reference for measuring an amount of corrosion thinning, is drawn on the inside of the pipeline in the first image; an amount-of-corrosion-thinning measurement unit 13 that calculates the amount of corrosion thinning on the basis of the second image; and a measurement data creation unit 14 that creates measurement data linking the calculated amount of corrosion thinning and the first image.

Description

[Technical Field]

[0001] The present disclosure relates to a measurement device, a measurement method, and a program. [Background technology]

[0002] Techniques for measuring corrosion-induced wall thinning in pipelines are currently known. Corrosion wall thinning refers to the corrosion depth relative to the thickness of the pipeline when the thickness of the metal material forming the pipeline is reduced due to corrosion. Among social infrastructure structures, a vast number of lifeline facilities, such as water supply and communications facilities, are installed underground and are essential to our daily lives, and are rapidly aging. Metallic pipelines, in particular, rust as they age, and this progression can lead to holes in the pipeline and other conditions that can cause a loss of functionality. Therefore, it is important to understand the corrosion depth relative to the thickness of the pipeline. Previous research has examined strength assessment methods for structural safety that take into account the amount of corrosion-induced wall thinning in pipelines using ultrasonic measurements or numerical analysis.

[0003] Non-Patent Document 1 describes the results of research into elucidating the corrosion deterioration mechanism of steel bridges and diagnosing their durability.

[0004] Non-Patent Document 2 describes the results of an analysis of the remaining strength of a compressed box-shaped member having an artificial cross-sectional defect.

[0005] Non-Patent Document 3 describes a deep learning-based framework for sewer pipe defect classification.

[0006] Meanwhile, a method has been developed that uses image recognition to classify images according to the level of rust progression.In recent years, research has been conducted into understanding the condition of metals using scanning electron microscopes (SEMs), and by utilizing SEMs, it has become possible to measure the amount of corrosion thinning in pipes.

[0007] Non-Patent Document 4 describes the results of a soundness assessment using machine learning based on images of corroded parts of steel bridges.

[0008] Non-Patent Document 5 describes a technique for analyzing the surface of a steel sheet using an electron microscope (SEM).

[0009] Furthermore, Non-Patent Document 6 describes the results of research into image recognition technology using deep learning in metal structure observation. [Prior art documents] [Non-patent literature]

[0010] [Non-Patent Document 1] Tetsuhiro Shimosato and four others, "Research on the Elucidation of Corrosion Deterioration Mechanisms and Durability Diagnosis of Steel Bridges, Report on the Results of Research and Development of Technology Contributing to the Improvement of the Quality of Road Policy," New Road Technology Conference, No. 21-5, 2012 [Non-patent document 2] Kyosuke Inoue et al., "Numerical Analysis of Compressive Load Carrying Capacity of Box Section Members of Steel Truss Bridges with Cross-Sectional Defects," Japan Society of Civil Engineers, Proceedings of Structural Engineering, Vol. 65A, pp. 76-89, 2019 [Non-patent document 3] Srinath Shiv Kumar et al., “Deep Learning-Based Automated Detection of Sewer Defects in CCTV Videos”, Journal of Computing in Civil Engineering , Vol.34, No.1 , 04019047 , 2020 [Non-patent document 4] Rina Hasuike and 1 other collaborators, "An attempt to determine the degree of deterioration of corroded steel parts in different corrosion environments using convolutional neural networks," Proceedings of AI and Data Science, Vol. 1, pp. 365-372, 2020 [Non-patent document 5] Masayasu Nagoshi, "Steel Plate Surface Analysis Technique Using Electron Microscope," Materials and Environment, Vol. 64, No. 9, pp. 381-387, 2015 [Non-patent document 6] Tomoki Awano et al., "Research on Image Recognition Technology Using Deep Learning in Metal Structure Observation," IHI Technical Report, Vol. 60, No. 1, pp. 52-59, 2020 Summary of the Invention [Problem to be solved by the invention]

[0011] However, it is difficult to identify the position of the inner surface of the pipe before it corrodes from the SEM image, which serves as the measurement reference.

[0012] Therefore, there was room for improvement in the technology for measuring the amount of corrosion thinning in pipelines.

[0013] In view of the above circumstances, an object of the present disclosure is to improve the technology for measuring the amount of corrosion thinning of a pipeline. [Means for solving the problem]

[0014] In order to solve the above problems, the measuring device of this embodiment is a measuring device that measures the amount of corrosion thinning of a pipeline, and includes an image information input unit that inputs a first image of the pipeline cross section photographed by SEM, a measurement reference line drawing unit that creates a second image in which a circle that serves as a measurement reference for the amount of corrosion thinning is drawn inside the pipeline in the first image, a corrosion thinning amount measuring unit that calculates the amount of corrosion thinning based on the second image, and a measurement data creation unit that creates measurement data that links the calculated amount of corrosion thinning to the first image.

[0015] In order to solve the above problem, the measurement method of this embodiment is a measurement method for measuring the amount of corrosion thinning of a pipeline, and executes the following steps using a measurement device: inputting a first image of the pipeline cross section photographed by SEM; creating a second image in which a circle is drawn inside the pipeline in the first image as a measurement standard for the amount of corrosion thinning; calculating the amount of corrosion thinning based on the second image; and creating measurement data that links the calculated amount of corrosion thinning to the first image.

[0016] In order to solve the above problem, a program according to this embodiment causes a computer to function as a measurement device. [Effects of the Invention]

[0017] According to the present disclosure, techniques for measuring the amount of corrosion thinning in a pipeline are improved. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a block diagram showing an example of the configuration of a measurement apparatus according to a first embodiment. [Figure 2] 10A and 10B are schematic diagrams illustrating the operation of a measurement reference line drawing unit. [Figure 3] FIG. 4 is a schematic diagram illustrating the operation of a corrosion thinning amount measuring unit. [Figure 4] 4 is a flowchart showing an example of a measurement method executed by the measurement apparatus according to the first embodiment. [Figure 5] FIG. 10 is a block diagram showing an example of the configuration of a measurement apparatus according to a second embodiment. [Figure 6] 10 is a photograph for explaining the operation of the element distribution drawing unit. [Figure 7] FIG. 2 is a block diagram showing a schematic configuration of a computer that functions as a measurement device. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The present invention is not limited to the following embodiments, and various modifications can be made within the scope of the present invention.

[0020] (First embodiment) Fig. 1 is a block diagram showing an example of the configuration of a measuring device 10 according to the first embodiment. As shown in Fig. 1, the measuring device 10 includes an image information input unit 11, a measurement reference line drawing unit 12, a corrosion thinning amount measuring unit 13, and a measurement data creation unit 14. The measuring device 10 measures the corrosion thinning amount of a pipeline.

[0021] The measurement reference line drawing unit 12, the corrosion thinning amount measuring unit 13, and the measurement data creating unit 14 constitute a control and arithmetic circuit (controller) 20. The control and arithmetic circuit 20 may be constituted by dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array), or may be constituted by a processor, or may be constituted by including both.

[0022] The image information input unit 11 inputs a first image of a pipe cross section taken by a scanning electron microscope (SEM). The first image is an SEM image taken by the SEM, and in this disclosure, is also referred to as an SEM image. The image information input unit 11 outputs the input SEM image to the measurement reference line drawing unit 12 and the measurement data creation unit 14.

[0023] The image information input unit 11 further inputs the pixel size per pixel of the first image (SEM image). The pixel size per pixel of the SEM image is used by the corrosion thinning amount measurement unit 13, which will be described later, when calculating the corrosion thinning amount. The image information input unit 11 outputs the pixel size per pixel of the input SEM image to the measurement reference line drawing unit 12.

[0024] The measurement reference line drawing unit 12 creates a second image by drawing a circle that serves as a measurement reference for the amount of corrosion thinning inside the pipeline in the first image (SEM image). The circle that serves as the measurement reference for the amount of corrosion thinning is, for example, a circle that corresponds to the inner surface of the pipeline before the pipeline corrodes.

[0025] FIG. 2 is a schematic diagram illustrating the operation of the measurement reference line drawing unit 12. The measurement reference line drawing unit 12 acquires multiple non-corroded points on the inner surface of the pipeline T in the SEM image acquired from the image information input unit 11. In the example of FIG. 2, three points p1(x1, y1) to p3(x3, y3) are acquired. The number of points to be acquired is not particularly specified, but it is desirable to acquire at least three points. The measurement reference line drawing unit 12 uses the coordinates of the acquired points to draw a reference circle by the least squares method. The formula for the least squares method is shown in the following equation (1).

[0026]

number

[0027]

number

[0028] The measurement reference line drawing unit 12 uses the value obtained from equation (2) to draw a circle that serves as a reference for measuring the amount of corrosion thinning in the SEM image. However, the inner diameter of the pipeline T may be determined by industrial standards, etc. In such cases, the calculation load for drawing the circle that serves as a reference for measuring the amount of corrosion thinning can be reduced by inputting the radius r as a known value. The measurement reference line drawing unit 12 outputs to the corrosion thinning amount measurement unit 13 the second image on which the circle that serves as the measurement reference for the amount of corrosion thinning has been drawn and the pixel size per pixel of the SEM image input from the image information input unit 11.

[0029] The corrosion-thinning amount measurement unit 13 calculates the amount of corrosion-thinning based on the second image. The corrosion-thinning amount measurement unit 13 acquires coordinates of multiple points on the boundary between the corroded area (corroded area) of the pipeline and the non-corroded area (sound area) in the second image. The corrosion-thinning amount measurement unit 13 determines the point farthest from the center (a, b) of the measurement reference circle as the maximum corrosion point among the acquired points, acquires the number of pixels between the measurement reference circle and the maximum corrosion point, and calculates the amount of corrosion-thinning by multiplying the acquired number of pixels by the pixel size per pixel of the SEM image. The corrosion-thinning amount measurement unit 13 outputs the calculated amount of corrosion-thinning to the measurement data creation unit 14.

[0030] FIG. 3 is a schematic diagram illustrating the operation of the corrosion wall-thinning amount measuring unit 13. As shown in FIG. 3, when there is an area C1 where corrosion has progressed from the inside to the outside of the pipeline T, three points p4 (x4, y4) to p6 (x6, y6) are acquired at the boundary between the corroded area and the sound area of ​​the pipeline T. If the distances from the center (a, b) of the measurement reference circle to the three points are l4, l5, and l6, respectively, l5 is the longest, and therefore the point of greatest corrosion is p5 (x5, y5). Then, the corrosion wall-thinning amount CL is calculated by multiplying the number of pixels between the measurement reference circle and the point of greatest corrosion p5 by the pixel size per pixel using the following equation (4): Corrosion thinning amount CL = number of pixels × pixel size per pixel (4)

[0031] The measurement data creation unit 14 creates measurement data that links the calculated corrosion thinning amount with the first image (SEM image) acquired by the image information input unit 11. For example, measurement data that links the corrosion thinning amount with the SEM image refers to data in which the numerical value of the corrosion thinning amount is plotted at the measurement point in the SEM image. The measurement data creation unit 14 outputs the measurement data to an external information processing device such as a server. The measurement data is stored in the information processing device and used for analyzing the progression level of corrosion in the pipeline, etc.

[0032] FIG. 4 is a flowchart showing an example of a measurement method executed by the measurement apparatus 10 according to the first embodiment.

[0033] In step S101, the image information input unit 11 inputs a first image (SEM image) of a pipe cross section photographed by an SEM. In this step S101, the image information input unit 11 also inputs the pixel size per pixel of the SEM image.

[0034] In step S102, the measurement reference line drawing unit 12 creates a second image in which a circle is drawn inside the pipe in the first image, the circle being used as a measurement reference for the amount of corrosion thinning.

[0035] In step S103, the corrosion thinning amount measuring unit 13 calculates the corrosion thinning amount based on the second image.

[0036] In step S104, the measurement data creation unit 14 creates measurement data that links the calculated corrosion thinning amount with the SEM image acquired by the image information input unit 11.

[0037] As described above, the measuring device 10 according to this embodiment inputs a first image of a pipeline cross section photographed by an SEM, creates a second image in which a circle is drawn inside the pipeline in the first image as a measurement reference for the amount of corrosion thinning, calculates the amount of corrosion thinning based on the second image, and then creates measurement data that links the calculated amount of corrosion thinning with the first image.

[0038] With this configuration, it is possible to identify the position of the inner surface of the pipeline before corrosion, which serves as a measurement reference, from the image captured by the SEM. This improves the accuracy of measuring the amount of corrosion thinning, thereby improving the technology for measuring the amount of corrosion thinning of pipelines.

[0039] (Second embodiment) 5 is a block diagram showing an example of the configuration of a measuring device 10A according to the second embodiment. As shown in FIG. 5, the measuring device 10A includes an image information input unit 11, a measurement reference line drawing unit 12A, a corrosion thinning amount measurement unit 13, a measurement data creation unit 14, and an element distribution drawing unit 15. The measuring device 10A according to this embodiment differs from the measuring device 10 according to the first embodiment in that the measurement reference line drawing unit 12 is replaced with the measurement reference line drawing unit 12A. The same components as those in the first embodiment are designated by the same reference numerals as those in the first embodiment, and descriptions thereof will be omitted where appropriate.

[0040] A control and arithmetic circuit (controller) 20A is configured by the measurement reference line drawing unit 12A, the corrosion thinning amount measuring unit 13, the measurement data creating unit 14, and the element distribution drawing unit 15. The control and arithmetic circuit 20A may be configured by dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array), or may be configured by a processor, or may be configured by including both.

[0041] The measurement reference line drawing unit 12A includes an element distribution drawing unit 15. The element distribution drawing unit 15 visualizes the distribution of elements in an SEM image. Specifically, the element distribution drawing unit 15 plots the element distribution in a first image (SEM image) to determine the boundary between a non-corroded area (healthy area) of the pipeline and a corroded area (corroded area). After the element distribution drawing unit 15 accurately determines the boundary between the corroded area and healthy area of ​​the pipeline, the measurement reference line drawing unit 12A creates a second image in which a circle is drawn to serve as a measurement reference for the amount of corrosion thinning.

[0042] Figure 6 is a photograph explaining the operation of the element distribution plotting unit 15. As shown in Figure 6, the element distribution plotting unit 15 makes it possible to grasp the boundary between corroded areas and healthy areas more accurately by overlaying an SEM image and an EDS image. EDS (element mapping) is a method of elemental analysis using characteristic X-rays, and visualizes the intensity distribution of the characteristic X-rays of elements or the concentration distribution of elements in an SEM image. C1 is the area where corrosion has progressed from the inside to the outside of the pipeline, and C2 is the area where corrosion has progressed from the outside to the inside of the pipeline.

[0043] As described above, the measurement device 10A according to this embodiment accurately determines the boundary between the corroded region and the sound region by plotting the element distribution on the SEM image.

[0044] This configuration makes it possible to more accurately obtain the coordinates of non-corroded areas inside the pipeline, thereby further improving the accuracy of measuring the amount of corrosion thinning in the pipeline, thereby improving the technology for measuring the amount of corrosion thinning in the pipeline.

[0045] A computer capable of executing program instructions can also be used to cause the above-described measuring devices 10 and 10A to function. FIG. 7 is a block diagram showing a schematic configuration of a computer 100 that functions as the measuring devices 10 and 10A. Here, the computer 100 may be a general-purpose computer, a dedicated computer, a workstation, a PC (Personal Computer), an electronic notepad, or the like. The program instructions may be program code, code segments, or the like for performing necessary tasks.

[0046] 7, the computer 100 includes a processor 110, a memory unit including a ROM (Read Only Memory) 120, a RAM (Random Access Memory) 130, and a storage 140, an input unit 150, an output unit 160, and a communication interface (I / F) 170. Each component is connected to each other via a bus 180 so as to be able to communicate with each other.

[0047] The ROM 120 stores various programs and various data. The RAM 130 temporarily stores programs or data as a working area. The storage 140 is configured with an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including an operating system and various data. In the present disclosure, the programs related to the present disclosure are stored in the ROM 120 or the storage 140.

[0048] Specifically, the processor 110 is a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), a digital signal processor (DSP), a system on a chip (SoC), or the like, and may be configured with multiple processors of the same or different types. The processor 110 reads a program from the ROM 120 or the storage 140 and executes the program using the RAM 130 as a working area, thereby controlling the above components and performing various arithmetic processing. Note that at least a part of the processing content may be implemented by hardware.

[0049] The program may be recorded on a recording medium readable by the measuring devices 10 and 10A. Using such a recording medium, the program can be installed in the measuring devices 10 and 10A. Here, the recording medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a CD-ROM, a DVD-ROM, a USB (Universal Serial Bus) memory, or the like. Furthermore, the program may be downloaded from an external device via a network.

[0050] The following additional notes are provided regarding the above-described embodiments.

[0051] (Additional note 1) A measuring device for measuring the amount of corrosion thinning of a pipeline, an interface for inputting a first image of a cross section of a pipe taken by an SEM; a controller that creates a second image in which a circle is drawn inside the pipeline in the first image as a measurement standard for the amount of corrosion thinning, calculates the amount of corrosion thinning based on the second image, and creates measurement data that links the calculated amount of corrosion thinning with the first image. (Additional note 2) 2. The measurement device according to claim 1, wherein the controller draws the circle serving as the measurement reference using a least squares method. (Additional note 3) The interface further inputs a pixel size per pixel of the first image; The controller acquires coordinates of a plurality of points in the second image for the boundary between a corroded area and a non-corroded area of ​​the pipeline, determines the point among the acquired points that is farthest from the center of the measurement reference circle as the most corroded point, acquires the number of pixels between the measurement reference circle and the most corroded point, and calculates the amount of corrosion thinning by multiplying the acquired number of pixels by the pixel size of one pixel in the first image. (Additional note 4) 4. The measuring device according to any one of claims 1 to 3, wherein the controller determines the boundary between a non-corroded area and a corroded area of ​​the pipeline by plotting an element distribution on the first image. (Additional note 5) A method for measuring the amount of corrosion thinning of a pipeline, comprising: A measurement method in which a first image of a pipe cross section taken by an SEM is input into a measurement device, a second image is created in which a circle is drawn inside the pipe in the first image as a measurement standard for the amount of corrosion thinning, the amount of corrosion thinning is calculated based on the second image, and measurement data is created that links the calculated amount of corrosion thinning to the first image. (Additional note 6) A non-transitory storage medium storing a program executable by a computer, the non-transitory storage medium storing the program causing the computer to function as the measuring device described in any one of appendixes 1 to 4.

[0052] Although the above-described embodiments have been described as typical examples, it will be apparent to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the present disclosure. Therefore, the present invention should not be interpreted as being limited by the above-described embodiments, and various modifications or alterations are possible without departing from the scope of the claims. For example, multiple building blocks shown in the block diagrams of the embodiments can be combined into one, or one building block can be divided. [Explanation of symbols]

[0053] 10,10A Measuring Device 11 Image information input section (interface) 12,12A Measurement reference line drawing section 13 Corrosion thinning measurement section 14 Measurement Data Creation Department 15 Element distribution drawing section 20,20A control operation circuit (controller) 100 computers 110 processors 120 ROM 130 RAM 140 Storage 150 Input section 160 Output section 170 Communication Interface (I / F) 180 Bus

Claims

1. A measuring device for measuring the amount of corrosion thinning of a pipeline, an image information input unit that inputs a first image of a pipe cross section photographed by an SEM; a measurement reference line drawing unit that creates a second image in which a circle that serves as a measurement reference for the corrosion thinning amount is drawn inside the pipeline in the first image; a corrosion thinning amount measuring unit that calculates the corrosion thinning amount based on the second image; a measurement data creation unit that creates measurement data that links the calculated corrosion thinning amount with the first image; A measuring device comprising:

2. The measurement device according to claim 1 , wherein the measurement reference line drawing unit draws the circle serving as the measurement reference by a least squares method.

3. the image information input unit further inputs a pixel size per pixel of the first image; 3. The measuring device according to claim 1, wherein the corrosion thinning amount measuring unit acquires coordinates of a plurality of points on the boundary between a corroded area and a non-corroded area of ​​the pipeline in the second image, determines the point among the acquired points that is farthest from the center of the circle that serves as the measurement reference as the most corroded point, acquires the number of pixels between the circle that serves as the measurement reference and the most corroded point, and calculates the amount of corrosion thinning amount by multiplying the acquired number of pixels by a pixel size per pixel of the first image.

4. 3. The measurement device according to claim 1, wherein the measurement reference line drawing unit further comprises an element distribution drawing unit that plots an element distribution on the first image to determine a boundary between a non-corroded area and a corroded area of ​​the pipeline.

5. A method for measuring the amount of corrosion thinning of a pipeline, comprising: By using measuring equipment, inputting a first image of a cross section of a pipe photographed by an SEM; creating a second image in which a circle serving as a measurement standard for the amount of corrosion thinning is drawn inside the pipe in the first image; calculating a corrosion thinning amount based on the second image; creating measurement data linking the calculated corrosion thinning amount with the first image; Measurement method to perform.

6. A program for causing a computer to function as the measurement device according to claim 1 or 2.

Images