Defect detection device

Abstract

To provide a defect detection device that can detect defects on the surface of the paper without irradiating it with light.SOLUTION: The defect detection device includes an image processing unit that detects defect candidates on the basis of infrared image data acquired by an infrared camera installed in one of the parts of a paper machine to capture an image of the surface of the paper being conveyed, and a defect determination unit that extracts a defect from the candidate defects. When the defect is extracted, a defect detection signal is generated and output to a control device.SELECTED DRAWING: Figure 1

Description

【Technical Field】 【0001】 Embodiments of the present invention relate to a defect inspection device for detecting defects in paper conveyed by a paper-making machine. 【Background Art】 【0002】 Conventionally, a defect inspection device uses a line sensor to inspect the presence or absence of paper defects. In such a defect inspection device, the presence or absence of defects is determined by irradiating the inspection target with light and detecting the presence or absence of the reflected light or transmitted light with a line sensor. 【0003】 As a specific example of a defect inspection device using a line sensor, a technique is known in which a plurality of line sensors are arranged apart in the paper conveyance direction to facilitate identification of the defect occurrence process. (For example, see Patent Document 1). 【Prior Art Documents】 【Patent Documents】 【0004】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2003-262593 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0005】 In recent years, it has become easier to use a visible light camera equipped with an area sensor for industrial applications, and it has become possible to detect defects in an inspection target by capturing a two-dimensional image of the target object and performing image analysis. 【0006】 On the other hand, in the case of a visible light camera, it is still necessary to irradiate the inspection target with light and detect the reflected light or transmitted light. When such a visible light camera is used for paper defect detection, it is necessary to secure a location for installing the camera and install lighting dedicated to defect detection. In an actual paper-making machine, since the machines for each process are intricate, there are limited positions where it is possible to secure a location for installing the camera and lighting. 【0007】 This invention was made to solve the above-mentioned problems, and aims to provide a defect detection device that can detect defects on the surface of paper without irradiating it with light. [Means for solving the problem] 【0008】 Embodiments of the present invention include: an image processing unit that detects candidate defects based on infrared image data representing the temperature distribution of paper acquired by an infrared camera installed in any part of a paper machine to image the surface of the paper being transported; a defect determination unit that extracts defects by removing disturbances from the candidate defects detected by the image processing unit; and an output unit that generates a defect detection signal and outputs it to a control device that controls the paper machine when the defect determination unit has extracted the defect. The defect detection unit removes disturbances by removing temperatures corresponding to human body temperature from the temperature distribution of the paper. . [Effects of the Invention] 【0009】 According to one embodiment, a defect detection device is provided that can detect defects on the surface of paper without irradiating it with light. [Brief explanation of the drawing] 【0010】 [Figure 1] This is a schematic block diagram illustrating a defect detection device according to an embodiment. [Figure 2] This is a schematic diagram illustrating the operation of the defect detection device according to the embodiment. [Figure 3] This is a schematic diagram illustrating the operation of the defect detection device according to the embodiment. [Figure 4] This is a schematic diagram illustrating the operation of the defect detection device according to the embodiment. [Figure 5] This is a schematic diagram illustrating the operation of the defect detection device according to the embodiment. [Figure 6] This is an example flowchart illustrating the operation of the defect detection device according to the embodiment. [Figure 7] This is a schematic diagram illustrating the relationship between visible light and infrared light. [Figure 8] This is a schematic diagram showing an infrared camera positioned inside the hood of the dry part. [Modes for carrying out the invention] 【0011】 The embodiments will be described below with reference to the drawings. Please note that the drawings are schematic or conceptual, and the relationships between the thickness and width of each part, as well as the ratios of the sizes of the parts, are not necessarily identical to those of reality. Furthermore, even when representing the same part, the dimensions and ratios may differ between drawings. In this specification and in each figure, elements similar to those described above are denoted by the same reference numerals, and detailed explanations are omitted as appropriate. 【0012】 Figure 1 is a schematic block diagram illustrating a defect detection device according to an embodiment. As shown in Figure 1, the defect detection device 8 is connected to the output of an infrared camera 1 located in one of the parts of the paper machine 100. In the example in Figure 1, the paper 5 is transported from right to left, and the infrared camera 1 is located on the exit side of the dry part 101. The infrared camera 1 captures an infrared image of the surface of the paper 5 discharged from the dry part 101, converts it into infrared image data, and outputs it to the defect detection device 8. Note that the infrared camera 1 is not limited to the example in Figure 1 and can be placed at any position in the paper machine 100. 【0013】 The defect detection device 8 is connected to the speed control system 20. The speed control system 20 controls the speed of the motors that drive the respective rolls for transporting the paper 5 in the paper making machine 100. In the speed control system 20, by appropriately controlling the speed of each motor, the paper 5 in each part is transported in the paper making machine 100 while being controlled to a desired tension. When the defect detection device 8 detects a defect in the paper 5, it generates a defect detection signal and outputs it to the speed control system 20. The speed control system 20 that receives the defect detection signal displays, for example, a warning indicating that a defect has been detected on the screen of the monitor. The operator who operates the speed control system 20 can check the screen and take appropriate measures in response to the displayed warning. 【0014】 The configuration of the defect detection device 8 according to the embodiment will be described. The defect detection device 8 includes an image processing unit 2, a defect determination unit 3, and an output unit 4. The image processing unit 2 is connected to the output of the infrared camera 1. The image processing unit 2 inputs the infrared image data acquired by the infrared camera 1, detects defect candidates by image processing of the infrared image, and outputs them to the defect determination unit 3. The defect determination unit 3 removes disturbances, determines defects from the defect candidates, and outputs information regarding the defects to the output unit 4. The output unit 4 generates a defect detection signal based on the defect information and outputs it to the speed control system 20. 【0015】 When the image processing unit 2 detects a defect candidate, it outputs the acquisition time of the infrared image data including the defect candidate as information on the defect candidate. The image processing unit 2 associates information on the position of the defect candidate, the size of the defect candidate, and information on the shape of the defect candidate with the acquisition time of the infrared image data and outputs it as information regarding the defect candidate. 【0016】 The defect determination unit 3 inputs the information on the defect candidates output by the image processing unit 2, and determines whether this information conforms to the conditions set in advance. The conditions set in advance are conditions related to the size and temperature of the defect candidates, as will be described later in relation to FIG. 6. In addition, conditions such as the shape of the defect candidates and the position of the defect candidates may be used as conditions. The position of the defect candidate is, for example, an end portion or a central portion along the conveyance direction of the paper 5. When the information on the defect candidate conforms to the conditions set in advance, the defect determination unit 3 determines that the defect candidate is a defect, and outputs the information on the defect candidate to the output unit 4 as information on the defect. When the information on the defect candidate does not conform to the conditions set in advance, the defect determination unit 3 may discard the information on the defect candidate, or may attach a flag indicating that it is information on a defect candidate that does not conform to the conditions and accumulate it as data in a separate database. Such data can be used when making the determination conditions of the defect determination unit 3 more accurate or more appropriate. 【0017】 The output unit 4 may transmit the information determined to be information on the defect by the defect determination unit 3 to another management system via a communication network (not shown). The other management system is, for example, a quality management server or a production management server. For example, in these systems that receive the information on the defect, it can be used as data for quality management and production management of the product in which the defect occurred. 【0018】 The operation of the defect detection device 8 according to the embodiment will be described. First, the operation of the image processing unit 2 will be described. FIGS. 2 to 5 are schematic diagrams for explaining the operation of the defect detection device according to the embodiment. FIG. 2 shows the position of the infrared camera 1 with respect to the paper 5 being conveyed. As shown in Figure 2, the infrared camera 1 is positioned to image the surface of the paper 5. In the examples in Figures 1 and 2, the infrared camera 1 is positioned opposite the surface of the paper 5 and images the paper 5 from above. The infrared camera 1 is positioned at an appropriate distance from the surface of the paper 5 so that the imaging range 11 includes the width of the paper 5 to be imaged. The infrared camera 1 is positioned directly above the surface of the paper 5, approximately in the center of the imaging range 11. 【0019】 In the example in Figure 2, the imaging range 11 is a rectangle with vertices 11a to 11d, and is shown by a dashed line. The imaging range 11 is set to include one end 5a and the other end 5b of the paper 5 along the paper transport direction. In other words, the imaging range 11 is set to include the entire width of the paper 5. 【0020】 Figure 3 schematically shows infrared image data D1 captured by infrared camera 1, and illustrates a specific example of applying XY coordinates to the infrared image data D1. The infrared image data D1 is represented by a solid rectangle. The upper end D1a of the infrared image data D1 corresponds to one end 5a of the paper 5 shown in Figure 2, and the lower end D1b corresponds to the other end 5b of the paper 5. 【0021】 In the example in Figure 3, the origin of the XY coordinate system is one vertex 11a of the imaging range 11. The transport direction of the paper 5 corresponds to the positive direction of the Y axis. The X axis, which is perpendicular to the Y axis, corresponds to the width direction of the paper 5. The vertex 11b of the imaging range 11 is at coordinate (X3,0), the vertex 11c is at coordinate (X3,Y1), and the vertex 11d is at coordinate (0,Y1). The upper end D1a of the infrared image data D1 extends from coordinate (X2,0) to coordinate (X2,Y1), and the lower end D1b extends from coordinate (X1,0) to coordinate (X1,Y1). 【0022】 The image processing unit 2 detects defect data D12 from such infrared image data D1. Defect data D12 corresponds to defect 12 shown in Figure 2. In the infrared image data D1, temperature data is associated with each XY coordinate. For example, infrared image data D1 is mesh data of the surface temperature of paper 5. Needless to say, defect 12 in Figure 2 and defect data D12 in Figure 3 are used by the image processing unit 2 to detect information about candidate defects. 【0023】 Figures 4 and 5 show the coordinate dependence of temperature data T associated with the XY coordinates. Figure 4 shows the X-coordinate dependence CX of temperature T when Y=Y0, and Figure 5 shows the Y-coordinate dependence CY of temperature T when X=X0. In other words, the intersection of the X-coordinate dependence CX and the Y-coordinate dependence CY in the XY coordinate system is the coordinate (X0,Y0) of the location of the defect data D12. 【0024】 As shown in Figure 4, the X-coordinate dependence of temperature T is as follows: From the origin 0 to the coordinate X1 of the lower end D1b, the temperature T2 is approximately constant, and is higher than T2, in the positive X-axis direction from the lower end D1b, i.e., from the other end 5b of the paper 5 in Figure 2 towards the inside of the paper 5, as seen in the X-coordinate. Near coordinate X0, the temperature T begins to decrease, reaching a temperature T0 that is lower than T1 at coordinate X0. Further in the positive X-axis direction, i.e., towards the one end 5a of the paper 5 in Figure 2, the temperature near coordinate X0 reaches a temperature T1 that is higher than T0, and is maintained at approximately constant up to the one end 5a. Beyond coordinate X2, it reaches the one end 5a in Figure 2, and reaches a temperature T2 that is lower than T1. 【0025】 As shown in Figure 5, the Y-coordinate dependence of temperature T in CY is as follows: from the origin 0, the temperature T1 is almost constant in the positive Y-axis direction, that is, along the paper transport direction 5 in Figure 2. Near coordinate Y0, the temperature begins to decrease, reaching a temperature T0 at coordinate Y0 that is lower than temperature T1. Further toward the positive Y-axis direction, that is, the paper transport direction 5 in Figure 2, the temperature becomes T1 near coordinate Y0 and remains almost constant toward the positive Y-axis direction. 【0026】 The image processing unit 2, for example, scans the infrared image data D1 in the X-axis and Y-axis directions, respectively, and detects changes in temperature data T for each XY coordinate. In the case of a defect, the temperature is lower than the surface temperature of the paper 5. For example, the image processing unit 2 can identify a defect by calculating the average value of the temperature data T obtained by scanning the entire XY coordinate system and extracting coordinates with low temperatures using the temperature difference or temperature change rate relative to a preset average value. 【0027】 If a region is formed by low-temperature coordinates, for example, the maximum length in the X-axis direction and the maximum length in the Y-axis direction can be defined as the size of the defect identified in that region, thereby determining a candidate defect and using this information as defect data. The shape of the candidate defect can be used as defect information by the coordinates of the outer perimeter that form the region of low-temperature coordinates. 【0028】 The image processing unit 2 extracts defect data D12 from the infrared image data D1 as described above, associates the acquisition time of the infrared image data D1, the location, size, and shape of the defect with the defect data D12, and outputs it to the defect determination unit 3. 【0029】 Furthermore, if a single infrared camera 1 cannot capture the entire width of the paper due to the width of the paper or constraints on the paper machine's layout, multiple infrared cameras can be arranged in the width direction of the paper to acquire image data simultaneously, for example. 【0030】 Next, the operation of the defect detection unit 3 will be described. Figure 6 is an example of a flowchart illustrating the operation of the defect detection device according to the embodiment. This flowchart explains the operation of the defect determination unit 3, which sets the defect data D12 output by the image processing unit 2 as a candidate defect and determines whether or not the defect data D12 is the defect 12 shown in Figure 2. 【0031】 As shown in Figure 6, in step S1, the defect determination unit 3 receives information about candidate defects from the image processing unit 2. 【0032】 In step S2, the defect determination unit 3 determines the size of the defect based on the information regarding the candidate defect. The defect determination unit 3 has a preset threshold for the size of the defect. If the size of the defect is greater than or equal to the preset threshold, the defect determination unit 3 proceeds to step S3. If the size of the defect is less than the preset threshold, the defect determination unit 3 determines that the defect data D12 is defect 12 and outputs the information regarding the candidate defect to the output unit 4 as information regarding the defect. 【0033】 In step S3, the defect determination unit 3 determines the temperature of the candidate defect as contained in the information regarding the candidate defect. A temperature threshold is pre-set for the defect determination unit 3. In the example in Figure 6, the temperature threshold is set to 35°C to 37°C. This threshold is set as the temperature when a worker is near the imaging range 11 of the infrared camera 1 and is captured in the infrared image data D1. If the temperature of the candidate defect is in the range of 35°C to 37°C, the defect determination unit 3 determines that the candidate defect is not defective. If the temperature of the candidate defect is lower than 35°C or higher than 37°C, the defect determination unit 3 determines that the candidate defect is defective. 【0034】 In this way, the defect detection unit 3 removes disturbances, determines a defect from the candidate defects, and outputs it to the output unit 4. 【0035】 The effects of the defect detection device 8 according to this embodiment will be described. Figure 7 is a schematic diagram illustrating the relationship between visible light and infrared light. The defect detection device 8 according to this embodiment determines the presence or absence of defects and detects defects based on infrared image data D1 acquired by the infrared camera 1 from the surface of the paper 5 being transported by the paper machine 100. As shown in Figure 7, infrared light has a longer wavelength than visible light. Objects emit electromagnetic waves with wavelengths corresponding to their temperature (near-infrared, mid-infrared, and far-infrared), so the temperature of an object can be measured by detecting the wavelength of the electromagnetic waves emitted by the object. The infrared camera 1 acquires infrared image data D1 representing the temperature distribution, so defects can be detected based on the temperature distribution of the target object, without relying on visible light. 【0036】 The infrared camera 1, which acquires infrared image data D1 including the temperature distribution of paper 5, detects infrared radiation of wavelengths corresponding to the temperature of the object, so there is no need to acquire reflected or transmitted light from visible light illumination. Therefore, there is no need to prepare and arrange lighting for acquiring image data, and it can be installed in dark places. 【0037】 Figure 8 is a schematic diagram showing an infrared camera positioned inside the hood of the dry part. As shown in Figure 8, since illumination is not required when the infrared camera 1 acquires infrared image data D1 representing the temperature distribution, it is possible to acquire infrared image data D1 representing the temperature distribution on the surface of the paper 5 being transported through the dry part 101, even when the dry part 101 is placed inside a hood that isolates it from the external environment. 【0038】 It is also possible to associate the shape of a defect with infrared image data D1, which includes temperature distribution data representing the defect. The defect shape data can then be recorded on a quality control server and used to improve quality. 【0039】 In the defect detection device 8 according to this embodiment, the image processing unit 2 can associate the coordinate data of the defect's location with the time the infrared image data D1 was acquired. For example, a quality control server can statistically process the defect's location information and its acquisition time to determine under what conditions a defect will occur at what location (edge ​​or center), which can be used to plan measures for improving product quality. 【0040】 Furthermore, in a paper machine, time-series data of the paper transport speed 5 and the diameter of the paper wound onto the winding reel can be acquired by a data acquisition device, etc. Therefore, based on the acquisition time of the defective infrared image data D1, the coordinate data of the defect's location, the transport speed data, and the paper diameter data, the location of the defect after winding can be calculated. By calculating the location of the defect after winding, the location of the defect can be identified, making it easier to remove the defect by rewinding. 【0041】 In this way, a defect detection device can be realized that can detect defects on the surface of paper without irradiating it with light. 【0042】 While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols] 【0043】 1…Infrared camera, 2…Image processing unit, 3…Defect detection unit, 4…Output unit, 5…Paper, 8…Defect detection device, 11…Imaging range, 12…Defect, 100…Paper machine, 101…Dry part

Claims

[Claim 1] An image processing unit detects candidate defects based on infrared image data representing the temperature distribution of the paper, which is acquired by an infrared camera installed in one of the parts of the paper machine to image the surface of the paper being transported. A defect determination unit extracts defects by removing disturbances from the candidate defects detected by the image processing unit, An output unit that generates a defect detection signal when the defect detection unit extracts the defect and outputs it to a control device that controls the paper machine, Equipped with, The defect detection unit is a defect detection device that removes disturbances by removing temperatures corresponding to human body temperature from the temperature distribution of the paper. [Claim 2] The image processing unit outputs the infrared image data in which the candidate defect was detected, associating it with information about the candidate defect. The defect detection device according to claim 1, wherein the data relating to the candidate defect includes at least one of the time the infrared image data was acquired, the size of the candidate defect, and the shape of the candidate defect.

Images