WO2023027068A1 - Weld inspection method, weld inspection system, and weld inspection program - Google Patents

Weld inspection method, weld inspection system, and weld inspection program Download PDF

Info

Publication number
WO2023027068A1
WO2023027068A1 PCT/JP2022/031714 JP2022031714W WO2023027068A1 WO 2023027068 A1 WO2023027068 A1 WO 2023027068A1 JP 2022031714 W JP2022031714 W JP 2022031714W WO 2023027068 A1 WO2023027068 A1 WO 2023027068A1
Authority
WO
WIPO (PCT)
Prior art keywords
weld
welding
data
shape
point cloud
Prior art date
Application number
PCT/JP2022/031714
Other languages
French (fr)
Japanese (ja)
Inventor
弘隆 村松
ニック フォール
Original Assignee
リンクウィズ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by リンクウィズ株式会社 filed Critical リンクウィズ株式会社
Publication of WO2023027068A1 publication Critical patent/WO2023027068A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
    • G01B21/18—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring depth
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
    • G01B21/20—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring contours or curvatures, e.g. determining profile

Definitions

  • the present invention relates to a welding inspection technique for inspecting a welded portion of a welded target member.
  • Patent Document 1 discloses a technique for inspecting the weld shape by acquiring point cloud data representing the three-dimensional shape of the weld bead using imaging means. It is
  • the present invention has been made in view of such a background, and an object thereof is to provide a welding inspection device with improved accuracy in judging the quality of weld beads.
  • the main invention of the present invention for solving the above problems is a welding inspection system for inspecting the shape of a welded portion of an object to be measured, wherein the shape of the object to be measured is measured in a predetermined measurement area to obtain shape data.
  • a shape data acquisition unit that acquires welded portion data based on the acquired shape data; an area setting unit that divides and sets the welded portion into a plurality of areas;
  • a welding evaluation unit that performs welding evaluation for each area based on criteria set individually for each area of It is a welding inspection device characterized by the following.
  • FIG. 1 is a diagram showing an overall configuration example of a welding inspection system 100 of Embodiment 1.
  • FIG. 2 is a diagram showing how the welding inspection system 100 of Embodiment 1 is used to inspect a welded portion of an object to be inspected.
  • 2 is a diagram showing a hardware configuration example of the terminal 1 according to the first embodiment;
  • FIG. 2 is a diagram showing a functional configuration example of the terminal 1 according to the first embodiment;
  • FIG. FIG. 5 is a diagram showing an example of a flowchart of a welding inspection method according to the first embodiment;
  • 3 is a diagram showing an example of 3D point cloud data acquired by a 3D point cloud data acquisition unit 101 according to Embodiment 1.
  • FIG. 4 is a diagram showing an example of a reference plane 60 according to Embodiment 1.
  • FIG. FIG. 4 is a diagram showing an example of a method for extracting weld point cloud data from three-dimensional point cloud data according to the first embodiment
  • 6 is a diagram showing an example of weld point cloud data 70 acquired by a weld point cloud data acquiring unit according to the first embodiment
  • FIG. FIG. 7 is a diagram showing an example of a method of setting grid intersections set on a reference plane 60 according to the first embodiment
  • FIG. 10 is a diagram showing an example of selecting points corresponding to a plurality of grid intersection points from the welded portion point group data by the approximate surface generation unit according to the second embodiment
  • FIG. 10 is a diagram showing an example of data of a plurality of points corresponding to each grid intersection selected by the approximate surface generation unit according to the second embodiment
  • FIG. 11 is a diagram showing an example of mesh (approximate surface) generation by the approximate surface generation unit 103 according to the second embodiment.
  • FIG. 10 is a diagram showing an example of a method of extracting point cloud data separated by a predetermined distance or more from a mesh (approximate surface) according to the second embodiment;
  • FIG. 10 is a diagram showing an example of weld point cloud data 80 extracted from the weld point cloud data according to the second embodiment;
  • FIG. 9 is a diagram showing an example of a result of setting an area on a plane including welded portion point cloud data 80 by an area dividing unit according to the second embodiment;
  • FIG. 10 is a diagram showing an example of a method for dividing a plane area by an area dividing unit according to the second embodiment;
  • FIG. 10 is a diagram showing an example of a method for determining defective welding in each divided area according to the second embodiment;
  • the present invention has, for example, the following configurations.
  • a welding inspection system for inspecting the shape of a welded portion of an object to be measured, a shape data acquisition unit that acquires shape data by measuring the shape of the object to be measured in a predetermined measurement area; a weld data acquisition unit that acquires weld data based on the acquired shape data; an area setting unit that divides and sets the welded portion into a plurality of areas; a welding evaluation unit that performs welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
  • a welding inspection system comprising: [Item 2] In the welding inspection system described in the item, The weld data acquired by the weld data acquisition unit includes information indicating the depth of the weld, The welding inspection system, wherein the welding evaluation unit performs the welding evaluation based on a depth determination threshold set for each of the plurality of areas.
  • the welding evaluation unit determines whether or not there is a portion having a depth exceeding the determination threshold in each of the plurality of areas, A weld inspection system characterized in that a weld is evaluated as defective if there is a portion with a depth exceeding .
  • the shape data acquisition unit acquires shape data of the object to be measured as three-dimensional point cloud data, The weld data acquisition unit generates an approximate plane based on a part of the point group selected from the three-dimensional point cloud data, and the perpendicular distance between the point group of the three-dimensional point cloud data and the approximate plane is predetermined.
  • a welding inspection system characterized by acquiring a point cloud exceeding a value as shape data of a weld.
  • the weld data acquisition unit generates a mesh composed of a plurality of triangles as an approximate surface using an approximate curve generated based on a partial point group selected from the three-dimensional point cloud data.
  • Weld inspection system characterized by: [Item 6] In the welding inspection system according to item 4 or item 5, The weld shape data acquisition unit sets a plurality of representative points on a plane of a reference plane defined based on coordinate information input by a user or pre-recorded coordinate information, and sets the plurality of representative points.
  • a welding inspection system characterized by selecting corresponding points closest to each other from the three-dimensional point group data and generating an approximate curve based on the plurality of selected corresponding points.
  • a welding inspection method for inspecting the shape of a welded portion of an object to be measured obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area; a step of acquiring data of the weld based on the acquired shape data; setting the weld zone by dividing it into a plurality of areas; a step of performing welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
  • a welding inspection method comprising: [Item 8] A welding inspection program for causing a computer to execute a welding inspection method for inspecting the shape of a welded portion of a measurement object, The welding inspection program includes, as the welding inspection method, A welding inspection method for inspecting the shape of a welded portion of an object to be measured, obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area
  • FIG. 1 is a diagram showing an example of a welding inspection system 100 of this embodiment.
  • the welding inspection system 100 of this embodiment has a terminal 1 , a working robot 2 and a controller 3 .
  • the working robot 2 has at least an arm 21 and a sensor 22 .
  • the terminal 1, the controller 3, and the working robot 2 are connected by wire or wirelessly so as to be able to communicate with each other.
  • FIG. 2 is a diagram showing how the welding inspection system 100 is used to inspect a welded portion of an object welded by laser welding or the like.
  • the sensor 22 provided on the arm 21 of the working robot 2 acquires point cloud data of the surface shape of a predetermined area including the welded portion 401 of the inspection object 4 .
  • FIG. 3 is a diagram showing the hardware configuration of the terminal 1.
  • the terminal 1 may be, for example, a general-purpose computer such as a personal computer, or may be logically realized by cloud computing. Note that the illustrated configuration is an example, and other configurations may be employed. For example, some functions provided in the processor 10 of the terminal 1 may be executed by an external server or another terminal.
  • the terminal 1 includes at least a processor 10 , a memory 11 , a storage 12 , a transmission/reception section 13 , an input/output section 14 and the like, which are electrically connected to each other through a bus 15 .
  • the processor 10 is an arithmetic device that controls the overall operation of the terminal 1, controls at least transmission and reception of data to and from the working robot 2, executes applications, and performs information processing necessary for authentication processing.
  • the processor 10 is a CPU (Central Processing Unit) and/or a GPU (Graphics Processing Unit), and executes programs for this system stored in the storage 12 and developed in the memory 11 to perform each information processing. .
  • the memory 11 includes a main memory composed of a volatile memory device such as a DRAM (Dynamic Random Access Memory), and an auxiliary memory composed of a non-volatile memory device such as a flash memory or a HDD (Hard Disc Drive). .
  • the memory 11 is used as a work area or the like for the processor 10, and stores a BIOS (Basic Input/Output System) executed when the terminal 1 is started, various setting information, and the like.
  • BIOS Basic Input/Output System
  • the storage 12 stores various programs such as application programs.
  • a database storing data used for each process may be constructed in the storage 12 .
  • the transmitting/receiving unit 13 connects the terminal 1 to at least the work robot 2, and transmits/receives data according to instructions from the processor.
  • the transmitting/receiving unit 13 is configured by wire or wireless, and in the case of wireless, for example, it may be configured by a short-range communication interface such as WiFi, Bluetooth (registered trademark), and BLE (Bluetooth Low Energy). .
  • the input/output unit 14 is configured by an information output device (eg, a display) and an information input device (eg, a keyboard and a mouse), and when configured by a smartphone or a tablet terminal. is composed of information input/output devices such as a touch panel.
  • a bus 15 is commonly connected to the above elements and transmits, for example, address signals, data signals and various control signals.
  • the working robot 2 has an arm 21 and a sensor 22.
  • the illustrated configuration is an example, and is not limited to this configuration.
  • the movement of the arm 21 is controlled by the terminal 1 based on the three-dimensional robot coordinate system.
  • the arm 21 may further include a controller 3 connected to the work robot 2 by wire or wirelessly, thereby controlling its operation.
  • the sensor 22 performs sensing of the inspection object 4 based on the three-dimensional sensor coordinate system.
  • the sensor 22 is, for example, a laser sensor that operates as a three-dimensional scanner, and obtains three-dimensional point cloud data 50 of the inspection object 4 by sensing.
  • the three-dimensional model data 50 is, for example, three-dimensional point cloud data as shown in FIG. 6, each point data has coordinate information of the sensor coordinate system, and the shape of the inspection object is grasped by the point cloud. becomes possible.
  • the sensor 22 is not limited to a laser sensor, and may be, for example, an image sensor using a stereo system or the like, or may be a sensor independent of the working robot. Anything that can acquire coordinate information can be used.
  • a configuration using three-dimensional point group data as the three-dimensional model data 50 will be described below as an example.
  • a predetermined calibration is performed before work, the robot coordinate system and the sensor coordinate system are associated with each other, and the user designates the position (coordinates) based on the sensor coordinate system.
  • the configuration may be such that the operation is controlled based on the position.
  • FIG. 4 is a block diagram illustrating functions implemented in the terminal 1.
  • the processor 10 of the terminal 1 includes a three-dimensional point cloud data acquisition unit (three-dimensional model data acquisition unit) 101, a reference plane setting unit 102, an approximate surface generation unit 103, and a weld point cloud data extraction unit. 104 , an area dividing section 105 and a welding evaluation section 106 .
  • the storage 12 of the terminal 1 also has a three-dimensional point cloud data storage unit (three-dimensional model data storage unit) 121 , a weld point cloud data storage unit 122 , and a welding evaluation result storage unit 123 .
  • the three-dimensional point cloud data acquisition unit 101 controls, for example, the working robot 2 according to instructions from the input/output unit 14 of the terminal 1, operates the arm 21 and the sensor 22, and obtains three-dimensional point cloud data of the inspection object 4. Get 40.
  • the operations of the arm 21 and the sensor 22 are set in advance so that the three-dimensional point cloud data of the area including the welded portion 401 of the inspection object 4 can be obtained.
  • the acquired 3D point cloud data is, for example, 3D coordinate information data based on the sensor coordinate system, and is stored in the 3D point cloud data storage unit 121 .
  • FIG. 6 is a diagram showing an example of the 3D point cloud data 40 acquired by the 3D point cloud data acquisition unit 101.
  • the three-dimensional point cloud data is three-dimensional point cloud data that is shape data of a region including the welded portion 401 of the inspection target 4.
  • the three-dimensional point cloud data is shape data of a region including the welded portion 401 of the inspection target 4.
  • the weld point cloud data acquisition unit 102 first obtains a reference for covering the weld area based on the position coordinate information indicating the weld area input by the user through the input/output unit 14 of the terminal 1 or recorded in the system in advance.
  • a plane 60 is set.
  • FIG. 7 is a diagram showing an example of a reference plane. As shown in FIG. 7, the reference plane 60 is input or preset by the user to be, for example, a plane that covers the area of the weld and is substantially parallel to the plane of the weld. Also, the area of the reference plane 60 is set by three or more points.
  • FIG. 8 is a diagram showing an example of extracting weld point cloud data 51 from three-dimensional point cloud data 50 based on the reference plane.
  • a point cloud existing in a position perpendicular to the reference plane 50 and overlapping with the reference plane is extracted as weld point cloud data 51, and the extracted weld point cloud data 51 is used as welding point cloud data.
  • the data is stored in the point cloud data storage unit 122 .
  • FIG. 9 is a diagram showing an example of the extracted weld point cloud data 51.
  • the extracted welded portion point cloud data 51 is the point cloud data of the area centering on the welded portion 401 .
  • the approximate plane generation unit 103 first sets grid intersection points 61 on the reference plane 60 .
  • FIG. 10 shows an example of a method of setting the grid intersection points on the reference plane 60 .
  • grid lines are defined at positions that vertically and horizontally divide the reference plane 60 into four equal parts, and 25 grid intersections, which are the intersections of the grid lines, are set.
  • the interval between grid lines does not necessarily have to be an interval that divides the reference plane into four equal parts, and can be set arbitrarily.
  • the approximate surface generation unit 103 selects points corresponding to a plurality of grid intersection points from the weld point cloud data.
  • FIG. 11 shows an example of selecting points corresponding to a plurality of grid intersection points from the weld point cloud data.
  • the point closest to each grid intersection point in the three-dimensional space is determined as the weld point.
  • Select from group data FIG. 12 shows an example of data of a plurality of points corresponding to grid intersection points obtained by the processing. Since the plurality of points shown in FIG. 12 are 25 point data selected from the weld point cloud data, they indicate the three-dimensional coordinates of the surface of the inspection object 4 .
  • FIG. 13 shows two-dimensionally an example of the approximate surface generation unit 103 generating an approximate surface from a mesh composed of a plurality of triangles.
  • an approximation curve is generated based on a plurality of point data corresponding to the grid intersection points selected by the above-described processing, and a mesh (approximation surface) composed of a plurality of triangles is generated by this approximation curve. do. It can be considered that the approximate surface generated in this manner approximates the surface shape of the original disk before the inspection object 4 is welded.
  • the weld point cloud data extraction unit 104 extracts point cloud data separated by a predetermined distance or more from the generated mesh (approximate surface).
  • FIG. 14 shows an example of a method of extracting point cloud data separated from a mesh (approximate surface) by a predetermined distance or more.
  • the weld point cloud data extraction unit 104 calculates the length of the vector orthogonal to the triangles forming the mesh for each point of the weld point cloud data, and calculates the distance from the mesh. If there are vectors orthogonal to multiple triangles, select the vector with the shortest distance. Then, points whose distance from the mesh is greater than a distance threshold input by the user or set in advance by the input/output unit 14 are extracted as the welded portion point cloud data 80 .
  • FIG. 15 is a diagram showing an example of weld point cloud data 80 extracted from the weld point cloud data based on the above process.
  • the point group separated from the mesh by a predetermined distance or more is the point group from the surface of the master disk of the inspection object 4. It can be regarded as data of a point group separated by a predetermined distance or more.
  • the area dividing unit 105 first sets an area on a plane containing the extracted weld point cloud data 80 . For example, based on the first and second points selected by the user via the terminal 1 a vector of the longitudinal direction of the planar area is defined, and based on the third selected point a short vector perpendicular to said longitudinal direction is defined. A vector of edge directions is defined.
  • the positions of both ends of the planar area are set based on the coordinates of the located points.
  • FIG. 16 is a diagram showing an example of a result of setting an area on a plane containing the weld point cloud data 80. As shown in FIG. As shown in FIG. 16 , the plane area 62 is set so that there is almost no marginal area outside the weld point cloud data 80 .
  • the area dividing unit 105 divides the set planar area into a plurality of areas.
  • FIG. 17 shows an example of a method of dividing a planar area. As shown in FIG. 17, for example, the planar area is divided into four areas by connecting the midpoints of the sides in the longitudinal direction and the lateral direction. Furthermore, the four divided areas are defined as three areas: the start area containing the welding start position, the end area containing the welding end position, and the main area containing the welded part between the welding start position and the end position. be done. For example, the area containing or closest to the first selected point by the user by terminal 1 is the start area, the area containing or closest to the second selected point is the end area, and the remaining two areas are merged. Each area after division can be defined as a main area.
  • the welding evaluation unit 106 sets different criteria for determining defective welding for each of the three defined areas, and determines defective welding based on the criteria.
  • FIG. 18 is a diagram showing an example of a method of determining defective welding in each divided area. As an example of welding defect determination, for example, as shown in FIG. are extracted for each area. A different threshold value for failure determination is provided for each of the three defined areas, and it is determined whether or not the deepest point of the concave portion in each area exceeds the threshold value for failure determination of the area. If there is a point in the area with a depth exceeding the failure determination threshold value, it is possible to determine that the weld is defective. Information on the evaluation results evaluated by welding evaluation unit 106 is stored in welding evaluation result storage unit 123 .
  • FIG. 5 is an example of a flowchart of a welding inspection method in the welding inspection system 100 of the first embodiment.
  • the user inputs a command to inspect the welded portion 401 of the inspection object 4 from the terminal 1, and operates the arm 21 and the sensor 22 to obtain the three-dimensional point cloud data acquisition unit 101, for example, FIG. acquires the reference three-dimensional point cloud data 50 of the inspection object 4 positioned on the workbench as shown in (step 101).
  • the weld point cloud data acquisition unit 102 sets a reference plane based on the information of a plurality of point coordinates input by the user through the terminal or information pre-recorded in the welding inspection system. For example, as shown in FIG. 7, the reference plane is set at a predetermined orientation and position that covers the area of the weld and is substantially parallel to the surface of the weld. Also, the area of the reference plane 60 may be set by three or more points. (Step 102).
  • the weld point cloud data acquisition unit 102 acquires the weld point cloud data existing within the area set by the reference plane 60 from the three-dimensional point cloud data 50 (step 103).
  • the point cloud existing in the vertical projection area of the reference plane 60 is obtained from the three-dimensional point cloud data 50, thereby extracting the weld point cloud data 51.
  • the point group to be extracted is not limited to those present in the vertical projection area strictly perpendicular to the reference plane 60 , and a point group present at a position substantially perpendicular to the reference plane 60 may be extracted.
  • the approximate surface generation unit 103 sets grid lines in a grid pattern vertically and horizontally on the reference plane 60 at predetermined intervals, and sets intersection points of the grid lines as grid intersection points (step 104).
  • grid lines are set at positions where the vertical and horizontal lengths of the reference plane 60 are 25%, and each intersection point is set as the grid intersection point 61 .
  • the approximate surface generation unit 103 selects corresponding points 52 with the closest three-dimensional coordinates for each grid intersection from the weld point cloud data (step 105).
  • FIG. 11 shows two-dimensionally the process of selecting this corresponding point 52 .
  • the approximate surface generation unit 103 generates an approximate curve based on the corresponding points 52, and creates a mesh (approximate surface) by the approximate curve (step 106).
  • FIG. 13 shows an image diagram of generating an approximate curve based on the corresponding points 52. As shown in FIG.
  • the weld point cloud data extracting unit 104 calculates the distance from each point of the weld point cloud data to the mesh (approximate surface), and extracts the points separated from the mesh by a predetermined distance or more into the weld point cloud data. 80 (step 107).
  • the mesh (approximate surface) is a surface approximating the master surface of the inspection object 4 before welding
  • the weld point cloud data 80 is projected from the master surface of the inspection object 4 before welding. It is a point cloud of a convex part and a concave part that are depressed.
  • the area dividing unit 105 sets a rectangular planar area 62 that includes the weld point cloud data 80 and has a small surplus area on the outside.
  • the plane area 62 is divided into four areas by vertically and horizontally dividing the plane area 62 into two at the center position, and the point including or closest to the point first selected by the user with the terminal 1 is divided into four areas.
  • the welding evaluation unit 106 measures the depth distance of the recess by calculating the distance of each point from the mesh 70 in each area, and outputs the maximum value of the depth of the recess for each area (step 108 ).
  • the maximum value of the recess depth measured for each area is compared with different determination thresholds set in advance for each area, so that the depth of the recess is determined by the determination threshold in at least one of the areas. It is also possible to determine that the weld is bad if there are points (portions) that are deeper than the value. Specifically, if there is a pit (a small recessed hole) that occurs on the surface of the weld bead, it can be determined that the weld is defective. Degradation can be detected.
  • the welding head tends to stay in the same position for a longer time in order to start welding in the welding start area, so the depth of the recess becomes deeper.
  • the depth of the concave portion is relatively shallow because the welding head moves stably at a constant speed.
  • convex portions to be formed in the end area.
  • the maximum depth of the concave portion can be measured for each area of the weld bead, and normality/abnormality can be determined for each area. It is possible to improve the accuracy of the welding failure determination compared to determining the welding failure using the determination threshold value.

Abstract

[Problem] The present invention addresses the problem of improving the accuracy in quality inspection of weld beads. [Solution] This weld inspection system is for inspecting the shape of a welded part of an object to be measured, and is characterized by comprising: a shape data acquisition unit which acquires shape data by measuring the shape of the to-be-measured object in a prescribed measurement region; a welded part data acquisition unit which acquires data of a welded part on the basis of the acquired shape data; an area setting unit which sets a plurality of areas by dividing the welded part; and a weld assessment unit which, on the basis of determination criteria that are set for each of the areas that have been set, conducts a weld assessment in the respective areas.

Description

溶接検査方法、溶接検査システム、溶接検査プログラムWelding Inspection Method, Welding Inspection System, Welding Inspection Program
　本発明は、溶接が行われた対象部材の溶接部分を検査する溶接検査技術に関する。 The present invention relates to a welding inspection technique for inspecting a welded portion of a welded target member.
　従来からレーザ溶接等によって形成される溶接ビードの検査が行われている。このようなレーザ溶接による溶接ビードの品質評価の一例として、例えば、特許文献１には、撮像手段により溶接ビードの三次元形状を表す点群データを取得して溶接形状の検査を行う技術が開示されている。 Conventionally, inspections of weld beads formed by laser welding, etc. have been carried out. As an example of quality evaluation of a weld bead by such laser welding, for example, Patent Document 1 discloses a technique for inspecting the weld shape by acquiring point cloud data representing the three-dimensional shape of the weld bead using imaging means. It is
特開２０１２－３７４８７号公報JP 2012-37487 A
　引用文献１に記載されたような溶接ビードの検査技術では、検査対象の断面形状に応じて生成したビード幅、ビード高さ、ビード重心、断面積の各特徴量を予め登録している許容範囲と比較して特徴量の良否を判定することが開示されている。しかし、溶接ビードの良否判定の精度をより向上させることが課題であった。 In the weld bead inspection technology as described in Cited Document 1, the allowable range in which each feature amount of bead width, bead height, bead center of gravity, and cross-sectional area generated according to the cross-sectional shape of the inspection target is registered in advance It is disclosed that the quality of the feature amount is determined by comparing with the . However, there has been a problem of improving the accuracy of determining the quality of the weld bead.
　本発明はこのような背景を鑑みてなされたものであり、溶接ビードの良否判定の精度が向上した溶接検査装置を提供することを目的とする。 The present invention has been made in view of such a background, and an object thereof is to provide a welding inspection device with improved accuracy in judging the quality of weld beads.
　上記課題を解決するための本発明の主たる発明は、計測対象物の溶接部の形状を検査する溶接検査システムであって、所定計測領域における前記計測対象物の形状を計測して形状データを取得する形状データ取得部と、取得した前記形状データに基づいて溶接部のデータを取得する溶接部データ取得部と、前記溶接部を複数のエリアに分けて設定するエリア設定部と、設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行う溶接評価部と、を含む、
ことを特徴とする溶接検査装置である。 The main invention of the present invention for solving the above problems is a welding inspection system for inspecting the shape of a welded portion of an object to be measured, wherein the shape of the object to be measured is measured in a predetermined measurement area to obtain shape data. a shape data acquisition unit that acquires welded portion data based on the acquired shape data; an area setting unit that divides and sets the welded portion into a plurality of areas; A welding evaluation unit that performs welding evaluation for each area based on criteria set individually for each area of
It is a welding inspection device characterized by the following.
　その他本願が開示する課題やその解決方法については、発明の実施形態の欄及び図面により明らかにされる。 Other problems disclosed by the present application and their solutions will be clarified in the section of the embodiment of the invention and the drawings.
　本発明によれば、溶接ビードの良否を自動的に判断できる溶接検査装置又は溶接検査方法を提供することができる。 According to the present invention, it is possible to provide a welding inspection device or a welding inspection method that can automatically determine the quality of a weld bead.
本実施形態１の溶接検査システム１００の全体構成例を示す図である。1 is a diagram showing an overall configuration example of a welding inspection system 100 of Embodiment 1. FIG. 本実施形態１の溶接検査システム１００を用いて検査対象物の溶接部を検査する様子を示す図である。FIG. 2 is a diagram showing how the welding inspection system 100 of Embodiment 1 is used to inspect a welded portion of an object to be inspected. 本実施形態１に係る端末１のハードウェア構成例を示す図である。2 is a diagram showing a hardware configuration example of the terminal 1 according to the first embodiment; FIG. 本実施形態１に係る端末１の機能構成例を示す図である。2 is a diagram showing a functional configuration example of the terminal 1 according to the first embodiment; FIG. 本実施形態１に係る溶接検査方法のフローチャート例を示す図である。FIG. 5 is a diagram showing an example of a flowchart of a welding inspection method according to the first embodiment; 本実施形態１に係る三次元点群データ取得部１０１により取得される三次元点群データの一例を示す図である。3 is a diagram showing an example of 3D point cloud data acquired by a 3D point cloud data acquisition unit 101 according to Embodiment 1. FIG. 本実施形態１に係る基準平面６０の一例を示す図である。4 is a diagram showing an example of a reference plane 60 according to Embodiment 1. FIG. 本実施形態１に係る三次元点群データから溶接部点群データを抽出する方法の一例を示す図である。FIG. 4 is a diagram showing an example of a method for extracting weld point cloud data from three-dimensional point cloud data according to the first embodiment; 本実施形態１に係る溶接部点群データ取得部により取得された溶接部点群データ７０の一例を示す図である。6 is a diagram showing an example of weld point cloud data 70 acquired by a weld point cloud data acquiring unit according to the first embodiment; FIG. 本実施形態１に係る基準平面６０上に設定するグリッド交点の設定方法の一例を示す図である。FIG. 7 is a diagram showing an example of a method of setting grid intersections set on a reference plane 60 according to the first embodiment; 本実施形態２に係る近似面生成部が複数のグリッド交点に対応する点を溶接部点群データから選択する一例を示す図である。FIG. 10 is a diagram showing an example of selecting points corresponding to a plurality of grid intersection points from the welded portion point group data by the approximate surface generation unit according to the second embodiment; 本実施形態２に係る近似面生成部が選択した各グリッド交点に対応する複数点のデータの一例を示す図である。FIG. 10 is a diagram showing an example of data of a plurality of points corresponding to each grid intersection selected by the approximate surface generation unit according to the second embodiment; 本実施形態２に係る近似面生成部１０３がメッシュ（近似面）を生成する一例を示す図である。FIG. 11 is a diagram showing an example of mesh (approximate surface) generation by the approximate surface generation unit 103 according to the second embodiment. 本実施形態２に係るメッシュ（近似面）から所定距離以上離れた点群データを抽出する方法の一例を示す図である。FIG. 10 is a diagram showing an example of a method of extracting point cloud data separated by a predetermined distance or more from a mesh (approximate surface) according to the second embodiment; 本実施形態２に係る溶接部点群データから抽出された溶接部点群データ８０の一例を示す図である。FIG. 10 is a diagram showing an example of weld point cloud data 80 extracted from the weld point cloud data according to the second embodiment; 本実施形態２に係るエリア分割部が溶接部点群データ８０を含む平面上のエリアを設定した結果の一例を示した図である。FIG. 9 is a diagram showing an example of a result of setting an area on a plane including welded portion point cloud data 80 by an area dividing unit according to the second embodiment; 本実施形態２に係るエリア分割部が平面エリアを分割する方法の一例を示す図である。FIG. 10 is a diagram showing an example of a method for dividing a plane area by an area dividing unit according to the second embodiment; 本実施形態２に係る分割した各エリアにおいて溶接不良を判定する方法の一例を示す図である。FIG. 10 is a diagram showing an example of a method for determining defective welding in each divided area according to the second embodiment;
　本発明の実施形態の内容を列記して説明する。本発明は、たとえば以下のような構成を備える。 The contents of the embodiments of the present invention will be listed and explained. The present invention has, for example, the following configurations.
［項目１］
　計測対象物の溶接部の形状を検査する溶接検査システムであって、
所定計測領域における前記計測対象物の形状を計測して形状データを取得する形状データ取得部と、
取得した前記形状データに基づいて溶接部のデータを取得する溶接部データ取得部と、
前記溶接部を複数のエリアに分けて設定するエリア設定部と、
設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行う溶接評価部と、
　を含む、ことを特徴とする溶接検査システム。
［項目２］
項目に記載の溶接検査システムにおいて、
　前記溶接部データ取得部の取得する前記溶接部のデータは、溶接部の深さを示す情報を含み、
　前記溶接評価部は、前記複数のエリア毎にそれぞれ設定された深さの判定しきい値に基づいて溶接評価を行う、ことを特徴とする溶接検査システム。
［項目３］
　項目３に記載の溶接検査システムにおいて、
　前記溶接評価部は、前記複数のエリア毎に当該エリア内に前記判定しきい値を超える深さとなる部分が存在するか否かを判定し、前記複数のエリアのいずれかにおいて前記判定しきい値を超える深さとなる部分が存在する場合に、溶接が不良であると評価する、ことを特徴とする溶接検査システム。
［項目４］
　項目１乃至３のいずれか１項に記載の溶接検査システムにおいて、
　前記形状データ取得部は、計測対象物の形状データを三次元点群データとして取得し、
　前記溶接部データ取得部は、前記三次元点群データから選択された一部の点群に基づいて近似面を生成し、前記三次元点群データの点群と前記近似面の垂直距離が所定値を超える点群を溶接部の形状データとして取得する、ことを特徴とする溶接検査システム。
［項目５］
　項目４に記載の溶接検査システムにおいて、
　前記溶接部データ取得部は、前記三次元点群データから選択された一部の点群に基づいて生成した近似曲線を用いて複数の三角形で構成されるメッシュを近似面として生成する、ことを特徴とする溶接検査システム。
［項目６］
　項目４又は項目５に記載の溶接検査システムにおいて、
　前記溶接部形状データ取得部は、ユーザにより入力された座標情報、又は予め記録された座標情報に基づいて定義される基準平面の平面上に複数の代表点を設定し、当該複数の代表点の各々について最も近い距離にある対応点を前記三次元点群データから選択し、選択された複数の前記対応点に基づいて近似曲線を生成する、ことを特徴とする溶接検査システム。
［項目７］
　計測対象物の溶接部の形状を検査する溶接検査方法であって、
　所定計測領域における前記計測対象物の形状を計測して形状データを取得するステップと、
取得した前記形状データに基づいて溶接部のデータを取得するステップと、
前記溶接部を複数のエリアに分けて設定するステップと、
設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行うステップと、
　を含む、ことを特徴とする溶接検査方法。
［項目８］
　計測対象物の溶接部の形状を検査する溶接検査方法をコンピュータに実行させるための溶接検査プログラムであって、
　前記溶接検査プログラムは、前記溶接検査方法として、
　計測対象物の溶接部の形状を検査する溶接検査方法であって、
　所定計測領域における前記計測対象物の形状を計測して形状データを取得するステップと、
取得した前記形状データに基づいて溶接部のデータを取得するステップと、
前記溶接部を複数のエリアに分けて設定するステップと、
設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行うステップと、
　をコンピュータに実行させる、ことを特徴とする溶接検査プログラム。
 
  [Item 1]
A welding inspection system for inspecting the shape of a welded portion of an object to be measured,
a shape data acquisition unit that acquires shape data by measuring the shape of the object to be measured in a predetermined measurement area;
a weld data acquisition unit that acquires weld data based on the acquired shape data;
an area setting unit that divides and sets the welded portion into a plurality of areas;
a welding evaluation unit that performs welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
A welding inspection system, comprising:
[Item 2]
In the welding inspection system described in the item,
The weld data acquired by the weld data acquisition unit includes information indicating the depth of the weld,
The welding inspection system, wherein the welding evaluation unit performs the welding evaluation based on a depth determination threshold set for each of the plurality of areas.
[Item 3]
In the welding inspection system according to item 3,
The welding evaluation unit determines whether or not there is a portion having a depth exceeding the determination threshold in each of the plurality of areas, A weld inspection system characterized in that a weld is evaluated as defective if there is a portion with a depth exceeding .
[Item 4]
In the welding inspection system according to any one of items 1 to 3,
The shape data acquisition unit acquires shape data of the object to be measured as three-dimensional point cloud data,
The weld data acquisition unit generates an approximate plane based on a part of the point group selected from the three-dimensional point cloud data, and the perpendicular distance between the point group of the three-dimensional point cloud data and the approximate plane is predetermined. A welding inspection system characterized by acquiring a point cloud exceeding a value as shape data of a weld.
[Item 5]
In the welding inspection system according to item 4,
The weld data acquisition unit generates a mesh composed of a plurality of triangles as an approximate surface using an approximate curve generated based on a partial point group selected from the three-dimensional point cloud data. Weld inspection system characterized by:
[Item 6]
In the welding inspection system according to item 4 or item 5,
The weld shape data acquisition unit sets a plurality of representative points on a plane of a reference plane defined based on coordinate information input by a user or pre-recorded coordinate information, and sets the plurality of representative points. A welding inspection system characterized by selecting corresponding points closest to each other from the three-dimensional point group data and generating an approximate curve based on the plurality of selected corresponding points.
[Item 7]
A welding inspection method for inspecting the shape of a welded portion of an object to be measured,
obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area;
a step of acquiring data of the weld based on the acquired shape data;
setting the weld zone by dividing it into a plurality of areas;
a step of performing welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
A welding inspection method comprising:
[Item 8]
A welding inspection program for causing a computer to execute a welding inspection method for inspecting the shape of a welded portion of a measurement object,
The welding inspection program includes, as the welding inspection method,
A welding inspection method for inspecting the shape of a welded portion of an object to be measured,
obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area;
a step of acquiring data of the weld based on the acquired shape data;
setting the weld zone by dividing it into a plurality of areas;
a step of performing welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
A welding inspection program characterized by causing a computer to execute
＜実施の形態１の詳細＞
　本発明の一実施形態に係る溶接検査システム１００の具体例を、以下に図面を参照しつつ説明する。なお、本発明はこれらの例示に限定されるものではなく、特許請求の範囲によって示され、特許請求の範囲と均等の意味及び範囲内でのすべての変更が含まれることが意図される。以下の説明では、添付図面において、同一または類似の要素には同一または類似の参照符号及び名称が付され、各実施形態の説明において同一または類似の要素に関する重複する説明は省略することがある。また、各実施形態で示される特徴は、互いに矛盾しない限り他の実施形態にも適用可能である。 <Details of Embodiment 1>
A specific example of a welding inspection system 100 according to one embodiment of the present invention will be described below with reference to the drawings. The present invention is not limited to these examples, but is indicated by the scope of the claims, and is intended to include all modifications within the scope and meaning equivalent to the scope of the claims. In the following description, the same or similar elements in the accompanying drawings are given the same or similar reference numerals and names, and duplicate descriptions of the same or similar elements may be omitted in the description of each embodiment. Also, the features shown in each embodiment can be applied to other embodiments as long as they are not mutually contradictory.
　図１は、本実施形態の溶接検査システム１００の一例を示す図である。図１に示されるように、本実施形態の溶接検査システム１００では、端末１と、作業用ロボット２、コントローラ３とを有している。作業用ロボット２は、少なくともアーム２１、センサ２２を有している。端末１、コントローラ３及び作業用ロボット２は、有線または無線にて互いに通信可能に接続されている。 FIG. 1 is a diagram showing an example of a welding inspection system 100 of this embodiment. As shown in FIG. 1 , the welding inspection system 100 of this embodiment has a terminal 1 , a working robot 2 and a controller 3 . The working robot 2 has at least an arm 21 and a sensor 22 . The terminal 1, the controller 3, and the working robot 2 are connected by wire or wirelessly so as to be able to communicate with each other.
　図２は、溶接検査システム１００を用いて、レーザ溶接等により溶接された検査対象物に対して、溶接部の検査を行う様子を示す図である。作業用ロボット２のアーム２１に設けられたセンサ２２により、検査対象物４の溶接部４０１を含む所定エリアの表面形状の点群データが取得される。 FIG. 2 is a diagram showing how the welding inspection system 100 is used to inspect a welded portion of an object welded by laser welding or the like. The sensor 22 provided on the arm 21 of the working robot 2 acquires point cloud data of the surface shape of a predetermined area including the welded portion 401 of the inspection object 4 .
＜端末１＞
　図３は、端末１のハードウェア構成を示す図である。端末１は、例えばパーソナルコンピュータのような汎用コンピュータとしてもよいし、或いはクラウド・コンピューティングによって論理的に実現されてもよい。なお、図示された構成は一例であり、これ以外の構成を有していてもよい。例えば、端末１のプロセッサ１０に設けられる一部の機能が外部のサーバや別端末により実行されてもよい。 <Terminal 1>
FIG. 3 is a diagram showing the hardware configuration of the terminal 1. As shown in FIG. The terminal 1 may be, for example, a general-purpose computer such as a personal computer, or may be logically realized by cloud computing. Note that the illustrated configuration is an example, and other configurations may be employed. For example, some functions provided in the processor 10 of the terminal 1 may be executed by an external server or another terminal.
　端末１は、少なくとも、プロセッサ１０、メモリ１１、ストレージ１２、送受信部１３、入出力部１４等を備え、これらはバス１５を通じて相互に電気的に接続される。 The terminal 1 includes at least a processor 10 , a memory 11 , a storage 12 , a transmission/reception section 13 , an input/output section 14 and the like, which are electrically connected to each other through a bus 15 .
　プロセッサ１０は、端末１全体の動作を制御し、少なくとも作業用ロボット２とのデータ等の送受信の制御、及びアプリケーションの実行及び認証処理に必要な情報処理等を行う演算装置である。例えばプロセッサ１０はＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）および／またはＧＰＵ（Ｇｒａｐｈｉｃｓ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）であり、ストレージ１２に格納されメモリ１１に展開された本システムのためのプログラム等を実行して各情報処理を実施する。 The processor 10 is an arithmetic device that controls the overall operation of the terminal 1, controls at least transmission and reception of data to and from the working robot 2, executes applications, and performs information processing necessary for authentication processing. For example, the processor 10 is a CPU (Central Processing Unit) and/or a GPU (Graphics Processing Unit), and executes programs for this system stored in the storage 12 and developed in the memory 11 to perform each information processing. .
　メモリ１１は、ＤＲＡＭ（Ｄｙｎａｍｉｃ　Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）等の揮発性記憶装置で構成される主記憶と、フラッシュメモリやＨＤＤ（Ｈａｒｄ　Ｄｉｓｃ　Ｄｒｉｖｅ）等の不揮発性記憶装置で構成される補助記憶と、を含む。メモリ１１は、プロセッサ１０のワークエリア等として使用され、また、端末１の起動時に実行されるＢＩＯＳ（Ｂａｓｉｃ　Ｉｎｐｕｔ　／　Ｏｕｔｐｕｔ　Ｓｙｓｔｅｍ）、及び各種設定情報等を格納する。 The memory 11 includes a main memory composed of a volatile memory device such as a DRAM (Dynamic Random Access Memory), and an auxiliary memory composed of a non-volatile memory device such as a flash memory or a HDD (Hard Disc Drive). . The memory 11 is used as a work area or the like for the processor 10, and stores a BIOS (Basic Input/Output System) executed when the terminal 1 is started, various setting information, and the like.
　ストレージ１２は、アプリケーション・プログラム等の各種プログラムを格納する。各処理に用いられるデータを格納したデータベースがストレージ１２に構築されていてもよい。 The storage 12 stores various programs such as application programs. A database storing data used for each process may be constructed in the storage 12 .
　送受信部１３は、端末１を少なくとも作業用ロボット２と接続し、プロセッサの指示に従い、データ等の送受信を行う。なお、送受信部１３は、有線または無線により構成されおり、無線である場合には、例えば、ＷｉＦｉやＢｌｕｅｔｏｏｔｈ（登録商標）及びＢＬＥ（Ｂｌｕｅｔｏｏｔｈ　Ｌｏｗ　Ｅｎｅｒｇｙ）の近距離通信インターフェースにより構成されていてもよい。 The transmitting/receiving unit 13 connects the terminal 1 to at least the work robot 2, and transmits/receives data according to instructions from the processor. The transmitting/receiving unit 13 is configured by wire or wireless, and in the case of wireless, for example, it may be configured by a short-range communication interface such as WiFi, Bluetooth (registered trademark), and BLE (Bluetooth Low Energy). .
　入出力部１４は、例えば端末１がパーソナルコンピュータで構成されている場合は情報出力機器（例えばディスプレイ）と情報入力機器（例えばキーボードやマウス）により構成され、スマートフォンまたはタブレット端末で構成されている場合はタッチパネル等の情報入出力機器により構成されている。 For example, when the terminal 1 is configured by a personal computer, the input/output unit 14 is configured by an information output device (eg, a display) and an information input device (eg, a keyboard and a mouse), and when configured by a smartphone or a tablet terminal. is composed of information input/output devices such as a touch panel.
　バス１５は、上記各要素に共通に接続され、例えば、アドレス信号、データ信号及び各種制御信号を伝達する。 A bus 15 is commonly connected to the above elements and transmits, for example, address signals, data signals and various control signals.
＜作業用ロボット２＞
　図１、図２に戻り、本実施形態に係る作業用ロボット２について説明する。 <Working robot 2>
Returning to FIGS. 1 and 2, the working robot 2 according to this embodiment will be described.
　上述のとおり、作業用ロボット２は、アーム２１と、センサ２２とを有する。なお、図示された構成は一例であり、この構成に限定されない。 As described above, the working robot 2 has an arm 21 and a sensor 22. Note that the illustrated configuration is an example, and is not limited to this configuration.
　アーム２１は、三次元のロボット座標系に基づき、端末１にその動作を制御される。また、アーム２１は、有線または無線で作業用ロボット２と接続されたコントローラ３をさらに備え、これによりその動作を制御されてもよい。 The movement of the arm 21 is controlled by the terminal 1 based on the three-dimensional robot coordinate system. In addition, the arm 21 may further include a controller 3 connected to the work robot 2 by wire or wirelessly, thereby controlling its operation.
　センサ２２は、三次元のセンサ座標系に基づき、検査対象物４のセンシングを行う。センサ２２は、例えば三次元スキャナとして動作するレーザセンサであり、センシングにより検査対象物４の三次元点群データ５０を取得する。三次元モデルデータ５０は、例えば、図６に示されるような三次元点群データであり、それぞれの点データがセンサ座標系の座標情報を有し、点群により検査対象物の形状を把握することが可能となる。なお、センサ２２は、レーザセンサに限らず、例えばステレオ方式などを用いた画像センサなどであってもよいし、作業用ロボットとは独立したセンサであってもよく、三次元のセンサ座標系における座標情報が取得できるものであればよい。また、説明を具体化するために、以下では三次元モデルデータ５０として、三次元点群データを用いた構成を一例として説明する。 The sensor 22 performs sensing of the inspection object 4 based on the three-dimensional sensor coordinate system. The sensor 22 is, for example, a laser sensor that operates as a three-dimensional scanner, and obtains three-dimensional point cloud data 50 of the inspection object 4 by sensing. The three-dimensional model data 50 is, for example, three-dimensional point cloud data as shown in FIG. 6, each point data has coordinate information of the sensor coordinate system, and the shape of the inspection object is grasped by the point cloud. becomes possible. The sensor 22 is not limited to a laser sensor, and may be, for example, an image sensor using a stereo system or the like, or may be a sensor independent of the working robot. Anything that can acquire coordinate information can be used. In addition, in order to make the description concrete, a configuration using three-dimensional point group data as the three-dimensional model data 50 will be described below as an example.
　なお、作業前に所定のキャリブレーションを行い、ロボット座標系及びセンサ座標系を互いに関連付け、例えばセンサ座標系を基にユーザが位置（座標）を指定することにより、アーム２１やセンサ２２が対応した位置を基に動作制御されるように構成をなしてもよい。 A predetermined calibration is performed before work, the robot coordinate system and the sensor coordinate system are associated with each other, and the user designates the position (coordinates) based on the sensor coordinate system. The configuration may be such that the operation is controlled based on the position.
＜端末１の機能＞
　図４は、端末１に実装される機能を例示したブロック図である。本実施の形態においては、端末１のプロセッサ１０は、三次元点群データ取得部（三次元モデルデータ取得部）１０１、基準平面設定部１０２、近似面生成部１０３、溶接部点群データ抽出部１０４、エリア分割部１０５、溶接評価部１０６を有している。また、端末１のストレージ１２は、三次元点群データ記憶部（三次元モデルデータ記憶部）１２１、溶接部点群データ記憶部１２２、溶接評価結果記憶部１２３を有している。 <Functions of Terminal 1>
FIG. 4 is a block diagram illustrating functions implemented in the terminal 1. As shown in FIG. In this embodiment, the processor 10 of the terminal 1 includes a three-dimensional point cloud data acquisition unit (three-dimensional model data acquisition unit) 101, a reference plane setting unit 102, an approximate surface generation unit 103, and a weld point cloud data extraction unit. 104 , an area dividing section 105 and a welding evaluation section 106 . The storage 12 of the terminal 1 also has a three-dimensional point cloud data storage unit (three-dimensional model data storage unit) 121 , a weld point cloud data storage unit 122 , and a welding evaluation result storage unit 123 .
　三次元点群データ取得部１０１は、端末１の入出力部１４からの指示により、例えば作業用ロボット２を制御し、アーム２１及びセンサ２２を動作させて検査対象物４の三次元点群データ４０を取得する。なお、検査対象物４の溶接部４０１を含む領域の三次元点群データを取得できるよう、アーム２１及びセンサ２２の動作は予め設定されている。取得した三次元点群データは、例えばセンサ座標系に基づく三次元座標情報データであり、三次元点群データ記憶部１２１に記憶される。 The three-dimensional point cloud data acquisition unit 101 controls, for example, the working robot 2 according to instructions from the input/output unit 14 of the terminal 1, operates the arm 21 and the sensor 22, and obtains three-dimensional point cloud data of the inspection object 4. Get 40. The operations of the arm 21 and the sensor 22 are set in advance so that the three-dimensional point cloud data of the area including the welded portion 401 of the inspection object 4 can be obtained. The acquired 3D point cloud data is, for example, 3D coordinate information data based on the sensor coordinate system, and is stored in the 3D point cloud data storage unit 121 .
図６は、三次元点群データ取得部１０１により取得される三次元点群データ４０の一例を示す図である。図６に示す通り、三次元点群データは検査対象物４の溶接部４０１を含む領域の形状データである三次元点群データである。 FIG. 6 is a diagram showing an example of the 3D point cloud data 40 acquired by the 3D point cloud data acquisition unit 101. As shown in FIG. As shown in FIG. 6, the three-dimensional point cloud data is three-dimensional point cloud data that is shape data of a region including the welded portion 401 of the inspection target 4. As shown in FIG.
　溶接部点群データ取得部１０２は、まず端末１の入出力部１４によりユーザが入力、もしくは予めシステムに記録された溶接部の領域を示す位置座標情報に基づいて、溶接部の領域を覆う基準平面６０を設定する。図７は、基準平面の一例を示す図である。図７に示すように、基準平面６０は、例えば、溶接部の領域を覆い、かつ溶接部の面と略平行な面となるようにユーザが入力又は予め設定される。また、基準平面６０は、３点またはそれ以上の数の点により領域が設定される。 The weld point cloud data acquisition unit 102 first obtains a reference for covering the weld area based on the position coordinate information indicating the weld area input by the user through the input/output unit 14 of the terminal 1 or recorded in the system in advance. A plane 60 is set. FIG. 7 is a diagram showing an example of a reference plane. As shown in FIG. 7, the reference plane 60 is input or preset by the user to be, for example, a plane that covers the area of the weld and is substantially parallel to the plane of the weld. Also, the area of the reference plane 60 is set by three or more points.
次に、溶接部点群データ取得部１０２は、基準平面６０に覆われたエリアの点群データを溶接部点群データ５１として取得する。図８は、基準平面に基づいて三次元点群データ５０から溶接部点群データ５１を抽出する一例を示す図である。図８に示す例では、基準平面５０に対して垂直方向であって、基準平面と重なる位置に存在する点群を溶接部点群データ５１として抽出し、抽出した溶接部点群データ５１を溶接部点群データ記憶部１２２に保存する。図９は、抽出した溶接部点群データ５１の一例を示す図である。図９に示す通り、抽出した溶接部点群データ５１は溶接部４０１を中心とした領域の点群データである。 Next, the weld point cloud data acquisition unit 102 acquires the point cloud data of the area covered by the reference plane 60 as the weld point cloud data 51 . FIG. 8 is a diagram showing an example of extracting weld point cloud data 51 from three-dimensional point cloud data 50 based on the reference plane. In the example shown in FIG. 8, a point cloud existing in a position perpendicular to the reference plane 50 and overlapping with the reference plane is extracted as weld point cloud data 51, and the extracted weld point cloud data 51 is used as welding point cloud data. The data is stored in the point cloud data storage unit 122 . FIG. 9 is a diagram showing an example of the extracted weld point cloud data 51. As shown in FIG. As shown in FIG. 9 , the extracted welded portion point cloud data 51 is the point cloud data of the area centering on the welded portion 401 .
　近似面生成部１０３は、まず基準平面６０上にグリッド交点６１を設定する。ここで、図１０に当該グリッド交点を基準平面６０上に設定する方法の一例を示す。図１０に示す例では、基準平面６０の縦横それぞれ４等分する位置にグリッド線を定義し、各グリッド線の交点である２５個のグリッド交点を設定する。グリッド線の間隔は必ずしも基準平面を４等分にする間隔である必要は無く、任意に設定することが可能である。 The approximate plane generation unit 103 first sets grid intersection points 61 on the reference plane 60 . Here, FIG. 10 shows an example of a method of setting the grid intersection points on the reference plane 60 . In the example shown in FIG. 10, grid lines are defined at positions that vertically and horizontally divide the reference plane 60 into four equal parts, and 25 grid intersections, which are the intersections of the grid lines, are set. The interval between grid lines does not necessarily have to be an interval that divides the reference plane into four equal parts, and can be set arbitrarily.
次に、近似面生成部１０３は、複数のグリッド交点に対応する点を溶接部点群データから選択する。ここで、図１１に複数のグリッド交点に対応する点を溶接部点群データから選択する一例を示す。図１１に示す通り、複数のグリッド交点の三次元座標情報と溶接部点群データの各点の三次元座標情報に基づいて、各グリッド交点から三次元空間における距離が最も近い点を溶接部点群データから選択する。当該処理により得られたグリッド交点に対応する複数点のデータの一例を図１２に示す。図１２に示す複数点は溶接部点群データから選択された２５個の点データであるため、検査対象物４の表面の三次元座標を示している。 Next, the approximate surface generation unit 103 selects points corresponding to a plurality of grid intersection points from the weld point cloud data. Here, FIG. 11 shows an example of selecting points corresponding to a plurality of grid intersection points from the weld point cloud data. As shown in FIG. 11, based on the three-dimensional coordinate information of a plurality of grid intersection points and the three-dimensional coordinate information of each point in the weld point cloud data, the point closest to each grid intersection point in the three-dimensional space is determined as the weld point. Select from group data. FIG. 12 shows an example of data of a plurality of points corresponding to grid intersection points obtained by the processing. Since the plurality of points shown in FIG. 12 are 25 point data selected from the weld point cloud data, they indicate the three-dimensional coordinates of the surface of the inspection object 4 .
　次に、近似面生成部１０３は、近似面を生成する。図１３は、近似面生成部１０３が複数の三角形により構成されるメッシュにより近似面を生成する一例を２次元で示している。図１３に示す通、上述した処理により選択されたグリッド交点に対応する複数個の点データに基づいて近似曲線を生成し、この近似曲線により複数の三角形で構成されるメッシュ（近似面）を生成する。このように生成された近似面は、検査対象物４が溶接される前の原盤の表面形状を近似しているものと考えることができる。 Next, the approximate surface generation unit 103 generates an approximate surface. FIG. 13 shows two-dimensionally an example of the approximate surface generation unit 103 generating an approximate surface from a mesh composed of a plurality of triangles. As shown in FIG. 13, an approximation curve is generated based on a plurality of point data corresponding to the grid intersection points selected by the above-described processing, and a mesh (approximation surface) composed of a plurality of triangles is generated by this approximation curve. do. It can be considered that the approximate surface generated in this manner approximates the surface shape of the original disk before the inspection object 4 is welded.
　溶接部点群データ抽出部１０４は、生成したメッシュ（近似面）から所定距離以上離れた点群データを抽出する。図１４は、メッシュ（近似面）から所定距離以上離れた点群データを抽出する方法の一例を示している。溶接部点群データ抽出部１０４は、溶接部点群データの各点について、メッシュを構成する三角形と直交するベクトルの長さを算出してメッシュからの距離を計算する。もし複数の三角形に対して直交するベクトルが存在する場合には最も距離の近いベクトルを選択する。そして、入出力部１４によりユーザが入力、又は予め設定された距離のしきい値よりも、メッシュからの距離が大きな点群を溶接部点群データ８０として抽出する。図１５は、上記処理に基づいて溶接部点群データから抽出された溶接部点群データ８０の一例を示す図である。図１５に示す通り、メッシュは検査対象物４が溶接される前の原盤の表面形状を近似しているため、メッシュから所定距離以上離れた点群は、検査対象物４の原盤の表面からの距離が所定以上離れた点群のデータであるとみなすことができる。 The weld point cloud data extraction unit 104 extracts point cloud data separated by a predetermined distance or more from the generated mesh (approximate surface). FIG. 14 shows an example of a method of extracting point cloud data separated from a mesh (approximate surface) by a predetermined distance or more. The weld point cloud data extraction unit 104 calculates the length of the vector orthogonal to the triangles forming the mesh for each point of the weld point cloud data, and calculates the distance from the mesh. If there are vectors orthogonal to multiple triangles, select the vector with the shortest distance. Then, points whose distance from the mesh is greater than a distance threshold input by the user or set in advance by the input/output unit 14 are extracted as the welded portion point cloud data 80 . FIG. 15 is a diagram showing an example of weld point cloud data 80 extracted from the weld point cloud data based on the above process. As shown in FIG. 15, since the mesh approximates the surface shape of the master disk before the inspection object 4 is welded, the point group separated from the mesh by a predetermined distance or more is the point group from the surface of the master disk of the inspection object 4. It can be regarded as data of a point group separated by a predetermined distance or more.
　エリア分割部１０５は、まず抽出した溶接部点群データ８０を含む平面上のエリアを設定する。例えば、端末１を介してユーザによって選択された１番目と２番目の点に基づいて平面エリアの長手方向のベクトルが定義され、３番目に選択された点に基づいて前記長手方向と直交する短い辺の方向のベクトルが定義される。ここで、当該平面上のエリアは溶接部点群データ８０の外側に余白が少ない狭いエリアとして設定することがより望ましいため、溶接部点群データ８０の長手方向及び短手方向のそれぞれの隅に位置する点座標に基づいて、平面エリアの両端の位置を設定する。図１６は、溶接部点群データ８０を含む平面上のエリアを設定した結果の一例を示した図である。図１６に示す通り、溶接部点群データ８０の外側に余白となるエリアがほとんど生じないように平面エリア６２が設定される。 The area dividing unit 105 first sets an area on a plane containing the extracted weld point cloud data 80 . For example, based on the first and second points selected by the user via the terminal 1 a vector of the longitudinal direction of the planar area is defined, and based on the third selected point a short vector perpendicular to said longitudinal direction is defined. A vector of edge directions is defined. Here, since it is more desirable to set the area on the plane as a narrow area with few margins outside the weld point cloud data 80, The positions of both ends of the planar area are set based on the coordinates of the located points. FIG. 16 is a diagram showing an example of a result of setting an area on a plane containing the weld point cloud data 80. As shown in FIG. As shown in FIG. 16 , the plane area 62 is set so that there is almost no marginal area outside the weld point cloud data 80 .
エリア分割部１０５は、次に設定した平面エリアを複数エリアに分割する。図１７は、平面エリアを分割する方法の一例を示している。図１７に示す通り、例えば、平面エリアは、長手方向と短手方向の各辺の中点を結ぶことで４つのエリアに分割される。更に、４つに分割されたエリアは、溶接の開始位置を含むスタートエリア、溶接が終了位置を含むエンドエリア、溶接の開始位置を終了位置の間の溶接部分を含むメインエリアの３エリアに定義される。例えば、端末１によりユーザによって１番目に選択された点を含む又は最も近いエリアをスタートエリア、２番目に選択された点を含む又は最も近いエリアをエンドエリア、残された２つのエリアを統合したエリアをメインエリア、として分割後の各エリアを定義することができる。 The area dividing unit 105 divides the set planar area into a plurality of areas. FIG. 17 shows an example of a method of dividing a planar area. As shown in FIG. 17, for example, the planar area is divided into four areas by connecting the midpoints of the sides in the longitudinal direction and the lateral direction. Furthermore, the four divided areas are defined as three areas: the start area containing the welding start position, the end area containing the welding end position, and the main area containing the welded part between the welding start position and the end position. be done. For example, the area containing or closest to the first selected point by the user by terminal 1 is the start area, the area containing or closest to the second selected point is the end area, and the remaining two areas are merged. Each area after division can be defined as a main area.
　溶接評価部１０６は、定義された３つのエリア毎にそれぞれ異なる溶接不良判定基準を設け、当該基準に基づいて溶接不良判定を行う。図１８は、分割した各エリアにおいて溶接不良を判定する方法の一例を示す図である。溶接不良判定の一例として、例えば、図１８に示すように、各エリアにおいて、メッシュ７０もしくは基準平面６０から溶接部点群データ８０の各点群までの距離を計測し、距離が最大となる点をエリア毎に抽出する。定義された３つのエリア毎に異なる不良判定しきい値を設け、各エリアにおける凹部の深さが最も深い点が当該エリアの不良判定しきい値を超えているか否かを判定し、いずれかのエリアにおいて不良判定しきい値を超える深さの点が存在する場合に当該溶接が不良である旨の不良判定を行うことができる。溶接評価部１０６で評価された評価結果の情報は、溶接評価結果記憶部１２３に記憶される。 The welding evaluation unit 106 sets different criteria for determining defective welding for each of the three defined areas, and determines defective welding based on the criteria. FIG. 18 is a diagram showing an example of a method of determining defective welding in each divided area. As an example of welding defect determination, for example, as shown in FIG. are extracted for each area. A different threshold value for failure determination is provided for each of the three defined areas, and it is determined whether or not the deepest point of the concave portion in each area exceeds the threshold value for failure determination of the area. If there is a point in the area with a depth exceeding the failure determination threshold value, it is possible to determine that the weld is defective. Information on the evaluation results evaluated by welding evaluation unit 106 is stored in welding evaluation result storage unit 123 .
＜溶接検査方法のフローチャート＞
　図５は、本実施の形態１の溶接検査システム１００における溶接検査方法のフローチャートの一例である。 <Flow chart of welding inspection method>
FIG. 5 is an example of a flowchart of a welding inspection method in the welding inspection system 100 of the first embodiment.
　まず、ユーザは、検査対象物４の溶接部４０１の検査を行う指令を端末１により入力し、アーム２１及びセンサ２２を動作させることにより、三次元点群データ取得部１０１により、例えば、図６に示すような作業台上に位置する検査対象物４の基準三次元点群データ５０を取得する（ステップ１０１）。 First, the user inputs a command to inspect the welded portion 401 of the inspection object 4 from the terminal 1, and operates the arm 21 and the sensor 22 to obtain the three-dimensional point cloud data acquisition unit 101, for example, FIG. acquires the reference three-dimensional point cloud data 50 of the inspection object 4 positioned on the workbench as shown in (step 101).
　次に、ユーザが端末により入力した複数の点座標の情報、又は溶接検査システムに予め記録されている情報に基づいて、溶接部点群データ取得部１０２は基準平面を設定する。基準平面は、例えば、図７に示すように、溶接部の領域を覆い、かつ溶接部の面と略平行となる所定の向きと位置に設定される。また、基準平面６０は、３点またはそれ以上の数の点により領域が設定されても良い。（ステップ１０２）。 Next, the weld point cloud data acquisition unit 102 sets a reference plane based on the information of a plurality of point coordinates input by the user through the terminal or information pre-recorded in the welding inspection system. For example, as shown in FIG. 7, the reference plane is set at a predetermined orientation and position that covers the area of the weld and is substantially parallel to the surface of the weld. Also, the area of the reference plane 60 may be set by three or more points. (Step 102).
　次に、溶接部点群データ取得部１０２により、基準平面６０により設定されたエリア内に存在する溶接部点群データを三次元点群データ５０から取得する（ステップ１０３）。この時、図８に示されるように、基準平面６０の垂直投影エリアに存在する点群を三次元点群データ５０から取得することで、溶接部点群データ５１を抽出する。ここで、抽出される点群は、基準平面６０の厳密に垂直な垂直投影エリアに存在するものに限られず、基準平面６０に略垂直な位置に存在する点群を抽出しても良い。 Next, the weld point cloud data acquisition unit 102 acquires the weld point cloud data existing within the area set by the reference plane 60 from the three-dimensional point cloud data 50 (step 103). At this time, as shown in FIG. 8, the point cloud existing in the vertical projection area of the reference plane 60 is obtained from the three-dimensional point cloud data 50, thereby extracting the weld point cloud data 51. FIG. Here, the point group to be extracted is not limited to those present in the vertical projection area strictly perpendicular to the reference plane 60 , and a point group present at a position substantially perpendicular to the reference plane 60 may be extracted.
　次に、近似面生成部１０３は、近似面を生成する前処理として、基準平面６０上に所定間隔で縦横に格子状のグリッド線を設定し、グリッド線の交点をグリッド交点として設定する（ステップ１０４）。図１０に示すグリッド交点の設定一例では、基準平面６０の縦横それぞれの長さが２５％の位置にグリッド線を設定して、各交点をグリッド交点６１として設定している。 Next, as preprocessing for generating an approximate surface, the approximate surface generation unit 103 sets grid lines in a grid pattern vertically and horizontally on the reference plane 60 at predetermined intervals, and sets intersection points of the grid lines as grid intersection points (step 104). In an example of setting the grid intersection points shown in FIG. 10 , grid lines are set at positions where the vertical and horizontal lengths of the reference plane 60 are 25%, and each intersection point is set as the grid intersection point 61 .
　近似面生成部１０３は、近似面を生成する前処理の次のステップとして、各グリッド交点について３次元座標の位置が最も近い対応点５２を溶接部点群データから選択する（ステップ１０５）。図１１はこの対応点５２を選択する処理を二次元的に示したものである。 As the next step of preprocessing for generating an approximate surface, the approximate surface generation unit 103 selects corresponding points 52 with the closest three-dimensional coordinates for each grid intersection from the weld point cloud data (step 105). FIG. 11 shows two-dimensionally the process of selecting this corresponding point 52 .
　次に、近似面生成部１０３は、対応点５２に基づいて近似曲線を生成し、近似曲線によるメッシュ（近似面）を作成する（ステップ１０６）。図１３は、対応点５２に基づいて近似曲線を生成するイメージ図を示している。 Next, the approximate surface generation unit 103 generates an approximate curve based on the corresponding points 52, and creates a mesh (approximate surface) by the approximate curve (step 106). FIG. 13 shows an image diagram of generating an approximate curve based on the corresponding points 52. As shown in FIG.
次に、溶接部点群データ抽出部１０４は、溶接部点群データの各点についてメッシュ（近似面）との距離を計算して、メッシュから所定距離以上離れた点群を溶接部点群データ８０として抽出する（ステップ１０７）。ここで、メッシュ（近似面）は、溶接前の検査対象物４の原盤表面を近似した面となっているため、溶接部点群データ８０は、溶接前の検査対象物４の原盤表面から出っ張っている凸部及び窪んでいる凹部の点群である。 Next, the weld point cloud data extracting unit 104 calculates the distance from each point of the weld point cloud data to the mesh (approximate surface), and extracts the points separated from the mesh by a predetermined distance or more into the weld point cloud data. 80 (step 107). Here, since the mesh (approximate surface) is a surface approximating the master surface of the inspection object 4 before welding, the weld point cloud data 80 is projected from the master surface of the inspection object 4 before welding. It is a point cloud of a convex part and a concave part that are depressed.
　次に、エリア分割部１０５は、図１６に示すように、溶接部点群データ８０を含み外側に余剰エリアが少ない矩形の平面エリア６２を設定する。次に、図１７に示すように、当該平面エリア６２を縦横それぞれ中央位置で２分割することにより、４つのエリアに分割し、端末１によりユーザによって１番目に選択された点を含む又は最も近いエリアをスタートエリア、２番目に選択された点を含む又は最も近いエリアをエンドエリア、残された２つのエリアを統合したエリアをメインエリア、として分割後の各エリアを定義することにより、スタートエリア、エンドエリア、メインエリアがそれぞれ定義される（ステップ１０８）。 Next, as shown in FIG. 16, the area dividing unit 105 sets a rectangular planar area 62 that includes the weld point cloud data 80 and has a small surplus area on the outside. Next, as shown in FIG. 17, the plane area 62 is divided into four areas by vertically and horizontally dividing the plane area 62 into two at the center position, and the point including or closest to the point first selected by the user with the terminal 1 is divided into four areas. By defining each area after division as the start area, the area containing or closest to the second selected point as the end area, and the area that integrates the remaining two areas as the main area, , an end area, and a main area are defined (step 108).
　次に、溶接評価部１０６は、各エリアにおいて各点のメッシュ７０からの距離を計算することで凹部の深さ距離を計測して、エリア毎に凹部深さの最大値を出力する（ステップ１０８）。本ステップでは、計測されたエリア毎の凹部深さの最大値を、エリア毎に予め設定されたそれぞれ異なる判定しきい値と比較することにより、少なくともいずれかのエリアにおいて凹部深さが判定しきい値よりも深い点（部分）が存在する場合に、溶接が不良であると判定することも可能である。具体的には、溶接ビードの表面に発生するピット（小さく窪んだ穴）が存在する場合に溶接不良と判定することができるため、ピット等が原因で生じる応力低下や腐食などの溶接部の性能低下を検出することができる。 Next, the welding evaluation unit 106 measures the depth distance of the recess by calculating the distance of each point from the mesh 70 in each area, and outputs the maximum value of the depth of the recess for each area (step 108 ). In this step, the maximum value of the recess depth measured for each area is compared with different determination thresholds set in advance for each area, so that the depth of the recess is determined by the determination threshold in at least one of the areas. It is also possible to determine that the weld is bad if there are points (portions) that are deeper than the value. Specifically, if there is a pit (a small recessed hole) that occurs on the surface of the weld bead, it can be determined that the weld is defective. Degradation can be detected.
　レーザ溶接等の溶接を行う場合、一般的に、溶接のスタートエリアでは溶接開始するために溶接ヘッドが同じ位置に滞在する時間が長くなる傾向があるため凹部の深さが深くなる。一方、メインエリアでは、溶接ヘッドが安定した定速移動するため比較的凹部の深さが浅い。また、エンドエリアで凸部が形成される傾向がある。このように、溶接のエリア毎に形成される溶接ビードの凹凸形状が異なるため、溶接エリアの溶接ビード凹部の最大深さが浅くても、溶接不良と判断すべきケースが存在する。 When welding such as laser welding is generally performed, the welding head tends to stay in the same position for a longer time in order to start welding in the welding start area, so the depth of the recess becomes deeper. On the other hand, in the main area, the depth of the concave portion is relatively shallow because the welding head moves stably at a constant speed. In addition, there is a tendency for convex portions to be formed in the end area. As described above, since the uneven shape of the weld bead formed in each welding area is different, there are cases where it should be determined that the weld is defective even if the maximum depth of the weld bead recess in the weld area is shallow.
上述したような技術によると、溶接ビードのエリア毎に凹部の最大深さを計測して、エリア毎に正常／異常の判定を行うことができるため、一つに溶接ビードに対して単一の判定しきい値を用いて溶接の不良を判定するよりも、溶接の不良判定の精度を向上させることができる。 According to the technique described above, the maximum depth of the concave portion can be measured for each area of the weld bead, and normality/abnormality can be determined for each area. It is possible to improve the accuracy of the welding failure determination compared to determining the welding failure using the determination threshold value.
　以上、本実施形態について説明したが、上記実施形態は本発明の理解を容易にするためのものであり、本発明を限定して解釈するためのものではない。本発明は、その趣旨を逸脱することなく、変更、改良され得ると共に、本発明にはその等価物も含まれる。 Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention, and is not intended to limit and interpret the present invention. The present invention can be modified and improved without departing from its spirit, and the present invention also includes equivalents thereof.
　　１　　　端末
　　２　　　作業用ロボット
　　３　　　コントローラ
　　４　　　検査対象物
　　１０　　プロセッサ
　　１１　　メモリ
　　１２　　ストレージ
　　１３　　送受信部
　　１４　　入出力部
　　１５　　バス
　　２１　　アーム
　　２２　　センサ
　　５０　　三次元点群データ
　　５１　　溶接部点群データ
　　５２　　対応点
６０　　基準平面
６１　　グリッド交点
６２　　平面エリア
７０　　メッシュ（近似面）
８０　　溶接部点群データ
　　１００　溶接検査システム
　　１０１　三次元点群データ取得部
　　１０２　溶接部点群データ取得部
　　１０３　近似面生成部
　　１０４　溶接部点群データ抽出部
　　１０５　エリア分割部
　　１０６　溶接評価部
　　１２１　三次元点群データ記憶部
　　１２２　溶接部点群データ記憶部
　　１２３　溶接評価結果記憶部
　　４０１　溶接部
 
 
  REFERENCE SIGNS LIST 1 terminal 2 working robot 3 controller 4 inspection object 10 processor 11 memory 12 storage 13 transmitter/receiver 14 input/output unit 15 bus 21 arm 22 sensor 50 three-dimensional point cloud data 51 weld point cloud data 52 corresponding points 60 reference plane 61 Grid intersection 62 Plane area 70 Mesh (approximate surface)
80 Weld point cloud data 100 Welding inspection system 101 Three-dimensional point cloud data acquisition unit 102 Weld point cloud data acquisition unit 103 Approximate surface generation unit 104 Weld point cloud data extraction unit 105 Area division unit 106 Weld evaluation unit 121 Three-dimensional Point cloud data storage unit 122 Welded portion point cloud data storage unit 123 Welding evaluation result storage unit 401 Welded portion

Claims (8)

  1. 　計測対象物の溶接部の形状を検査する溶接検査システムであって、
    所定計測領域における前記計測対象物の形状を計測して形状データを取得する形状データ取得部と、
    取得した前記形状データに基づいて溶接部のデータを取得する溶接部データ取得部と、
    前記溶接部を複数のエリアに分けて設定するエリア設定部と、
    設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行う溶接評価部と、
    　を含む、ことを特徴とする溶接検査システム。     A welding inspection system for inspecting the shape of a welded portion of an object to be measured,
    a shape data acquisition unit that acquires shape data by measuring the shape of the object to be measured in a predetermined measurement area;
    a weld data acquisition unit that acquires weld data based on the acquired shape data;
    an area setting unit that divides and sets the welded portion into a plurality of areas;
    a welding evaluation unit that performs welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
    A welding inspection system, comprising:
  2. 請求項１に記載の溶接検査システムにおいて、
    　前記溶接部データ取得部の取得する前記溶接部のデータは、溶接部の深さを示す情報を含み、
    　前記溶接評価部は、前記複数のエリア毎にそれぞれ設定された深さの判定しきい値に基づいて溶接評価を行う、ことを特徴とする溶接検査システム。     The weld inspection system of claim 1, wherein
    The weld data acquired by the weld data acquisition unit includes information indicating the depth of the weld,
    The welding inspection system, wherein the welding evaluation unit performs the welding evaluation based on a depth determination threshold set for each of the plurality of areas.
  3. 　請求項２に記載の溶接検査システムにおいて、
    　前記溶接評価部は、前記複数のエリア毎に当該エリア内に前記判定しきい値を超える深さとなる部分が存在するか否かを判定し、前記複数のエリアのいずれかにおいて前記判定しきい値を超える深さとなる部分が存在する場合に、溶接が不良であると評価する、ことを特徴とする溶接検査システム。     The weld inspection system of claim 2,
    The welding evaluation unit determines whether or not there is a portion having a depth exceeding the determination threshold in each of the plurality of areas, A weld inspection system characterized in that a weld is evaluated as defective if there is a portion with a depth exceeding .
  4. 　請求項１乃至３のいずれか１項に記載の溶接検査システムにおいて、
    　前記形状データ取得部は、計測対象物の形状データを三次元点群データとして取得し、
    　前記溶接部データ取得部は、前記三次元点群データから選択された一部の点群に基づいて近似面を生成し、前記三次元点群データの点群と前記近似面の垂直距離が所定値を超える点群を溶接部の形状データとして取得する、ことを特徴とする溶接検査システム。     In the welding inspection system according to any one of claims 1 to 3,
    The shape data acquisition unit acquires shape data of the object to be measured as three-dimensional point cloud data,
    The weld data acquisition unit generates an approximate plane based on a part of the point group selected from the three-dimensional point cloud data, and the perpendicular distance between the point group of the three-dimensional point cloud data and the approximate plane is predetermined. A welding inspection system characterized by acquiring a point cloud exceeding a value as shape data of a weld.
  5. 　請求項４に記載の溶接検査システムにおいて、
    　前記溶接部データ取得部は、前記三次元点群データから選択された一部の点群に基づいて生成した近似曲線を用いて複数の三角形で構成されるメッシュを近似面として生成する、ことを特徴とする溶接検査システム。     The weld inspection system of claim 4,
    The weld data acquisition unit generates a mesh composed of a plurality of triangles as an approximate surface using an approximate curve generated based on a partial point group selected from the three-dimensional point cloud data. Weld inspection system characterized by:
  6. 　請求項４又は請求項５に記載の溶接検査システムにおいて、
    　前記溶接部形状データ取得部は、ユーザにより入力された座標情報、又は予め記録された座標情報に基づいて定義される基準平面の平面上に複数の代表点を設定し、当該複数の代表点の各々について最も近い距離にある対応点を前記三次元点群データから選択し、選択された複数の前記対応点に基づいて近似曲線を生成する、ことを特徴とする溶接検査システム。
          In the welding inspection system according to claim 4 or claim 5,
    The weld shape data acquisition unit sets a plurality of representative points on a plane of a reference plane defined based on coordinate information input by a user or pre-recorded coordinate information, and sets the plurality of representative points. A welding inspection system characterized by selecting corresponding points closest to each other from the three-dimensional point group data and generating an approximate curve based on the plurality of selected corresponding points.
  7. 　計測対象物の溶接部の形状を検査する溶接検査方法であって、
    　所定計測領域における前記計測対象物の形状を計測して形状データを取得するステップと、
    取得した前記形状データに基づいて溶接部のデータを取得するステップと、
    前記溶接部を複数のエリアに分けて設定するステップと、
    設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行うステップと、
    　を含む、ことを特徴とする溶接検査方法。
          A welding inspection method for inspecting the shape of a welded portion of an object to be measured,
    obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area;
    a step of acquiring data of the weld based on the acquired shape data;
    setting the weld zone by dividing it into a plurality of areas;
    a step of performing welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
    A welding inspection method comprising:
  8. 　計測対象物の溶接部の形状を検査する溶接検査方法をコンピュータに実行させるための溶接検査プログラムであって、
    　前記溶接検査プログラムは、前記溶接検査方法として、
    　計測対象物の溶接部の形状を検査する溶接検査方法であって、
    　所定計測領域における前記計測対象物の形状を計測して形状データを取得するステップと、
    取得した前記形状データに基づいて溶接部のデータを取得するステップと、
    前記溶接部を複数のエリアに分けて設定するステップと、
    設定された複数のエリア毎に個別に設定された判定基準に基づいて、エリア毎に溶接評価を行うステップと、
    　をコンピュータに実行させる、ことを特徴とする溶接検査プログラム。     A welding inspection program for causing a computer to execute a welding inspection method for inspecting the shape of a welded portion of a measurement object,
    The welding inspection program includes, as the welding inspection method,
    A welding inspection method for inspecting the shape of a welded portion of an object to be measured,
    obtaining shape data by measuring the shape of the object to be measured in a predetermined measurement area;
    a step of acquiring data of the weld based on the acquired shape data;
    setting the weld zone by dividing it into a plurality of areas;
    a step of performing welding evaluation for each area based on criteria individually set for each of the plurality of set areas;
    A welding inspection program characterized by causing a computer to execute
PCT/JP2022/031714 2021-08-24 2022-08-23 Weld inspection method, weld inspection system, and weld inspection program WO2023027068A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-136481 2021-08-24
JP2021136481A JP6990476B1 (en) 2021-08-24 2021-08-24 Welding inspection method, welding inspection system, welding inspection program

Publications (1)

Publication Number Publication Date
WO2023027068A1 true WO2023027068A1 (en) 2023-03-02

Family

ID=80185455

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/031714 WO2023027068A1 (en) 2021-08-24 2022-08-23 Weld inspection method, weld inspection system, and weld inspection program

Country Status (2)

Country Link
JP (2) JP6990476B1 (en)
WO (1) WO2023027068A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116673572A (en) * 2023-07-31 2023-09-01 天津悦华阀门科技有限公司 Mechanical welding data management analysis system based on artificial intelligence

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000158134A (en) * 1998-11-24 2000-06-13 Chuo Motor Wheel Co Ltd Arc welding stability judging method and device
JP2008246536A (en) * 2007-03-30 2008-10-16 Ihi Corp Apparatus and method for analyzing welding state
JP2012037487A (en) * 2010-08-11 2012-02-23 Koatec Kk Shape inspection device and shape inspection method
JP2014014856A (en) * 2012-07-11 2014-01-30 Suzuki Motor Corp Image processing method and image processing system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000158134A (en) * 1998-11-24 2000-06-13 Chuo Motor Wheel Co Ltd Arc welding stability judging method and device
JP2008246536A (en) * 2007-03-30 2008-10-16 Ihi Corp Apparatus and method for analyzing welding state
JP2012037487A (en) * 2010-08-11 2012-02-23 Koatec Kk Shape inspection device and shape inspection method
JP2014014856A (en) * 2012-07-11 2014-01-30 Suzuki Motor Corp Image processing method and image processing system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116673572A (en) * 2023-07-31 2023-09-01 天津悦华阀门科技有限公司 Mechanical welding data management analysis system based on artificial intelligence
CN116673572B (en) * 2023-07-31 2023-09-26 天津悦华阀门科技有限公司 Mechanical welding data management analysis system based on artificial intelligence

Also Published As

Publication number Publication date
JP2023031026A (en) 2023-03-08
JP6990476B1 (en) 2022-01-12
JP2023031195A (en) 2023-03-08

Similar Documents

Publication Publication Date Title
JP4052323B2 (en) 3D measurement system
US11426876B2 (en) Information processing apparatus, information processing method, and program
KR101918168B1 (en) Method for performing 3D measurement and Apparatus thereof
JP4112812B2 (en) Pattern evaluation method, pattern evaluation apparatus, and computer-readable recording medium
WO2023027068A1 (en) Weld inspection method, weld inspection system, and weld inspection program
US20090289953A1 (en) System and method for adjusting view of a measuring report of an object
KR101403377B1 (en) Method for calculating 6 dof motion of object by using 2d laser scanner
TW201915482A (en) On-line measuring system, coordinate calibrating method, deviation measuring method and computer-readable medium
US11481971B2 (en) Information processing method, information processing system, and program
KR100994742B1 (en) The method of collision detection and passpoint generation for moving path in 3 dimensional coordinate measuring machine
JP6778338B2 (en) Techniques for inspecting semiconductor wafers
US11662194B2 (en) Measurement point determination for coordinate measuring machine measurement paths
JP7079047B1 (en) Work system, work method
JP6796899B1 (en) Information processing method, information processing system, program
JP7156531B2 (en) Inspection support device, inspection support method and program
JP2019121076A (en) Information processing device, program and information processing method
JP2021124485A (en) Shape detection method, shape detection system, and program
JP6758695B1 (en) Shape detection method, shape detection system, program
JP6742661B1 (en) Shape detection method, shape detection system, program
JP7108329B1 (en) Information processing method, information processing system, program
JP6232947B2 (en) Flatness detection apparatus and flatness detection method
CN104457709A (en) Distance detection method of and electronic equipment
JP7156522B2 (en) Member identification device, member identification method and program
JP6991489B2 (en) Map evaluation device, map evaluation method and map evaluation program
JP2021125194A (en) Shape detection method, shape detection system, and program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22861356

Country of ref document: EP

Kind code of ref document: A1