CN109590952B - Intelligent detection method and detection workbench for complete process assembly plate - Google Patents
Intelligent detection method and detection workbench for complete process assembly plate Download PDFInfo
- Publication number
- CN109590952B CN109590952B CN201811541923.2A CN201811541923A CN109590952B CN 109590952 B CN109590952 B CN 109590952B CN 201811541923 A CN201811541923 A CN 201811541923A CN 109590952 B CN109590952 B CN 109590952B
- Authority
- CN
- China
- Prior art keywords
- assembly plate
- detected
- laser ranging
- dimensional imaging
- guide rail
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000003384 imaging method Methods 0.000 claims abstract description 41
- 230000005477 standard model Effects 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims description 41
- 238000007599 discharging Methods 0.000 claims description 16
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 230000010365 information processing Effects 0.000 claims description 10
- 230000033001 locomotion Effects 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 abstract 1
- 230000005540 biological transmission Effects 0.000 description 5
- 230000003137 locomotive effect Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25H—WORKSHOP EQUIPMENT, e.g. FOR MARKING-OUT WORK; STORAGE MEANS FOR WORKSHOPS
- B25H1/00—Work benches; Portable stands or supports for positioning portable tools or work to be operated on thereby
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/52—Devices for transferring articles or materials between conveyors i.e. discharging or feeding devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
- B65G47/90—Devices for picking-up and depositing articles or materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses an intelligent detection method of a complete process assembly plate, which comprises the following steps: collecting image information of a mounting plate to be detected, and identifying the type of the mounting plate to be detected and a position area of a workpiece on the mounting plate based on the image information; performing precise laser ranging on the position area based on the identification information in the previous step, and searching for a standard model of the assembly plate matched with the assembly plate to be detected; performing three-dimensional imaging on the assembly plate to be detected through a point cloud imaging algorithm based on the precise laser ranging data, acquiring a precise three-dimensional imaging model of the assembly plate to be detected, and positioning a workpiece; and calling the standard model of the assembly plate to be matched with the accurate three-dimensional imaging model, and detecting the sizes, shapes and positions of all workpieces on the assembly plate to be detected. The invention can realize intelligent real-time detection of the process assembly plate, saves a great deal of manpower, and has higher accuracy and operation efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to an intelligent detection method and a detection workbench for a complete process assembly plate (KIT plate).
Background
Locomotive overhaul is a key for ensuring safe running of a locomotive, locomotives of different levels can be overhauled in a certain period, and a large number of complete process assembly plates (called KIT plates for short) are used in the overhaul process. The KIT board is composed of component holes and components, and the assembly work of the KIT board is to insert various components into the corresponding component holes. The KIT boards with different types are inserted into various components with specified specifications, the work of assembling the KIT boards is mostly completed manually, and the work of assembling the KIT boards is completed by mechanized equipment in a small part. Component dimensional and quantity errors may occur during assembly due to omission and negligence. This phenomenon can introduce additional effort to the locomotive service personnel to check the component dimensions and increase the risk of service using components of the wrong dimensions.
Because of various types of KIT boards, the KIT boards are different in size and specification of components, and the arrangement intervals among the components are relatively close, the assembled KIT boards can only be inspected manually. The manual examination of KIT boards is inefficient and the accuracy of the examination is not satisfactory. There is therefore a great need to develop an automated smart device that can automatically detect KIT board assembly accuracy to overcome the above-described problems and drawbacks.
Disclosure of Invention
The invention provides an intelligent detection method and a detection workbench for a complete process assembly plate (KIT plate) for solving the problems.
The technical scheme adopted for solving the technical problems is as follows:
the first aspect of the invention provides an intelligent detection method for a complete process assembly plate, which comprises the following steps:
s1, collecting image information of a to-be-detected assembly plate, and identifying the type of the to-be-detected assembly plate and a position area of a workpiece on the assembly plate based on the image information;
s2, carrying out precise laser ranging on the position area based on the identification information in the S1, and searching a standard model of the assembly plate matched with the assembly plate to be detected;
s3, performing three-dimensional imaging on the to-be-detected assembly plate through a point cloud imaging algorithm based on the precise laser ranging data, acquiring a precise three-dimensional imaging model of the to-be-detected assembly plate, and positioning a workpiece;
s4, calling the standard model of the assembly plate to be matched with the accurate three-dimensional imaging model, and detecting the sizes, shapes and positions of all workpieces on the accurate three-dimensional imaging model to judge whether the assembly plate to be detected corresponding to the accurate three-dimensional imaging model is qualified or not.
Further, the step of S4 of calling the standard model of the assembly plate to match with the accurate three-dimensional imaging model specifically includes:
s41, placing the standard model of the assembly plate and the accurate three-dimensional imaging model in a coordinate space with a scanning plane of an XOY plane and a scanning height value of Z, wherein each pixel point in the model is represented by an (x, y, Z) vector;
s42, die setThe region in the XOY scanning plane is divided into L small block regions, the center position of each small block region is calculated, and a value vector p of a center point is obtained i ＝(x i ,y i ,z i ) I=1, 2, k L, and the value vectors of all the center points form a center point value vector set;
s43, for each center point p i Order-makingFor point p i The corresponding covariance matrix of the neighbor point set is shown in the following formula:
wherein ,is->Is defined by the center of gravity of (2); let lambda get 1 ,λ 2 ,λ 3 Is 3 eigenvalues of C and satisfies lambda 1 ≥λ 2 ≥λ 3 Then p is i The corresponding normal vector is lambda 3 Corresponding feature vectors, and further obtain p i Corresponding normal vector n i I.e. matching pairs: (p) i ,n i )；
S44, matching any two points in the vector set of the central point of the standard model of the assembly plateMatching pair +.A matching pair of any two points in the vector set of the central point value of the accurate three-dimensional imaging model>Respectively calculating the distance between the two points and the normal vector included angle:
and />
And the calculated result is compared with a preset geometric rigidity threshold tau dist And a normal vector shift threshold τ angle Comparing;
s45, if the matching pair of any two points in the accurate three-dimensional imaging model center point value vector set and the matching pair of any two points in the assembly plate standard model center point value vector set meet the following conditions:
|d S -d T |≤τ dist
|θ S -θ T |≤τ angle
the accurate three-dimensional imaging model is deemed to match the mounting plate standard model.
A second aspect of the present invention provides a complete process assembly plate inspection station comprising:
the system comprises a two-dimensional high-speed motion control platform, a high-definition industrial camera, a laser ranging module and a control host;
the two-dimensional high-speed motion control platform comprises a main body frame, a detection workbench movably mounted on a vertical guide rail in the main body frame, a feeding conveying belt positioned in front of the detection workbench, and a first discharging conveying belt and a second discharging conveying belt positioned behind the detection workbench;
the main body frame is provided with a first guide rail above the feeding conveyor belt, a first mechanical clamping device is movably mounted on the first guide rail, the main body frame is provided with a second guide rail above the first discharging conveyor belt and the second discharging conveyor belt, and a second mechanical clamping device is movably mounted on the second guide rail;
the center part of the detection workbench is in a hollowed-out design, a third guide rail and a fourth guide rail are respectively arranged above and below the detection workbench on the main body frame, a first high-definition industrial camera and a first laser ranging module are movably installed on the third guide rail, and a second high-definition industrial camera and a second laser ranging module are movably installed on the fourth guide rail;
the control host is respectively and electrically connected with the conveying driving motors of the feeding conveyor belt, the first discharging conveyor belt and the second discharging conveyor belt, and the displacement driving motors of the detection workbench, the first mechanical clamping device, the second mechanical clamping device, the first high-definition industrial camera, the first laser ranging module, the second high-definition industrial camera and the second laser ranging module are used for controlling the operation of the conveyor belts and the displacement of each part on the corresponding guide rail; the control host is also respectively in communication connection with the first high-definition industrial camera, the first laser ranging module, the second high-definition industrial camera and the second laser ranging module, and is used for receiving images or ranging information and performing corresponding processing.
Further, the displacement driving motor is a high-power high-precision alternating current servo motor.
Further, the control host is an embedded intelligent processor and comprises a drive control module and an information processing module, wherein the drive control module comprises an embedded motion control component taking a DSP chip as a core, and the information processing module comprises an embedded microprocessor and a memory.
Furthermore, the main body frame is also provided with man-machine interaction equipment, and the man-machine interaction equipment is connected with the control host and used for controlling instruction input and processing result display.
Furthermore, the main body frame is also provided with an audible and visual alarm device, and the audible and visual alarm device is connected with the control host and is used for sending out audible and visual alarm signals.
Compared with the prior art, the invention has the beneficial effects that:
according to the intelligent detection algorithm, firstly, the type of the assembly plate to be detected and the position area of the workpiece on the assembly plate are identified based on the collected image data, the standard model of the assembly plate corresponding to the assembly plate to be detected is searched, laser ranging is further carried out, the three-dimensional model of the assembly plate to be detected is constructed based on the laser ranging data, and then the three-dimensional model is compared and matched with the searched standard model of the assembly plate, and the assembly plate to be detected is comprehensively detected, so that the intelligent detection of the assembly plate is completed, and the detection efficiency and accuracy are greatly improved. Especially, the matching of the standard model of the assembly plate and the accurate three-dimensional imaging model is realized, and the neighborhoods with different capacities are divided according to the requirements, so that the calculation amount of point cloud matching is reduced; meanwhile, compared with the traditional point cloud matching algorithm, the method has higher efficiency, higher recognition rate and higher precision.
The detection workbench disclosed by the invention can automatically complete the detection of the assembly accuracy of the KIT plate by combining the intelligent detection method, can completely replace manual detection, and saves manpower. Meanwhile, a large number of detection results can be analyzed according to the process specification, and the assembly operation link of the KIT plate is further guided, so that the risks caused by overhauling by using the wrong number or wrong specification of parts are fundamentally reduced.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of an intelligent detection method of the present invention.
Fig. 2 (a) and (b) are schematic diagrams illustrating the division of the scanning area and other areas according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an embodiment of the inspection workbench of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the drawings and the specific examples, which are given by way of illustration only and are not intended to limit the scope of the invention, in order to facilitate a better understanding of the invention to those skilled in the art.
Example 1
The embodiment is an intelligent detection method for a complete process assembly plate, comprising the following steps:
first, image information of a mounting board to be detected is collected, and the type of the mounting board to be detected and a position area of a workpiece on the mounting board are identified based on the image information.
The image information can be acquired by an industrial camera, and the basic size and shape of the assembly plate to be detected can be acquired after image recognition, so that the type of the assembly plate can be recognized, and the position area of a workpiece on the assembly plate can be acquired.
And secondly, carrying out precise laser ranging on the position area of the mounting tool on the mounting plate to be detected based on the identification information in the first step, and simultaneously calling a mounting plate standard model matched with the mounting plate to be detected from a database based on the image identification result.
The precise laser ranging can be performed by a precise laser ranging device, and the upper surface and the lower surface of the assembly plate are generally measured to obtain overall measurement data. The standard model of the assembly plate can be pre-selected, generated and stored, and based on the image identification information, the basic matching of the assembly plate to be detected and the standard model of the assembly plate can be realized, so that the corresponding standard model of the assembly plate can be selected.
And thirdly, performing three-dimensional imaging on the assembly plate to be detected through a point cloud imaging algorithm based on the precise laser ranging data, so as to obtain an accurate three-dimensional imaging model of the assembly plate to be detected, and positioning a workpiece.
The three-dimensional imaging method based on ranging or scanning data is widely applied to industries such as 3D scanning printing, and more published documents are available for those skilled in the art to acquire, and the specific imaging method does not influence the implementation of the technical scheme of the invention, so the detailed description is omitted here.
And fourthly, calling the standard model of the assembly plate to be matched with the accurate three-dimensional imaging model, and detecting the sizes, shapes and positions of all workpieces on the accurate three-dimensional imaging model to judge whether the assembly plate to be detected corresponding to the accurate three-dimensional imaging model is qualified or not.
As a preferred embodiment, with reference to fig. 1, the matching process described above employs the following method:
(1) Placing the standard model of the assembly plate and the accurate three-dimensional imaging model in a coordinate space with a scanning plane of an XOY plane and a scanning height value of Z, wherein each pixel point in the model is represented by an (x, y, Z) vector, and the whole model is composed of corresponding point clouds;
(2) As shown in fig. 2 (a) and (b), the region of the model in the XOY scanning plane is equally divided into L small block regions, and the center position of each small block region is calculated to obtain a value vector p of the center point i ＝(x i ,y i ,z i ) I=1, 2, kl; all centersThe value vectors of the points form a central point value vector set;
(3) For each center point p i The calculation of its normal vector depends on the covariance analysis of its neighborhood, namely: p is p i The normal vector of (2) depends on covariance analysis of other points in the region; order theThe corresponding covariance matrix of the neighbor point set for the point pi is shown in the following formula:
wherein ,is->Is defined by the center of gravity of (2); let lambda get 1 ,λ 2 ,λ 3 Is 3 eigenvalues of C and satisfies lambda 1 ≥λ 2 ≥λ 3 Then p is i The corresponding normal vector is lambda 3 Corresponding feature vectors, and further obtain p i Corresponding normal vector n i I.e. matching pairs: (p) i ,n i )；
(4) Performing similar point cloud processing on the standard model of the assembly plate; thus, the matching pair of any two points in the central point value vector set corresponding to the standard model of the assembly plateMatching pair +.f of any two points in the central point value vector set corresponding to the accurate three-dimensional imaging model>Respectively calculating the distance between the two points and the normal vector included angle:
and the calculated result is compared with a preset geometric rigidity threshold tau dist And a normal vector shift threshold τ angle Comparing;
(5) If the matching pair of any two points in the center point value vector set corresponding to the accurate three-dimensional imaging model and the matching pair of any two points in the center point value vector set corresponding to the assembly plate standard model meet the following conditions:
|d S -d T |≤τ dist (4)
|θ S -θ T |≤τ angle (5)
the accurate three-dimensional imaging model is considered to be in accordance with a standard model, namely, the assembly plate to be detected corresponding to the accurate three-dimensional imaging model is considered to be a qualified product; otherwise, the defect is regarded as a defective product.
Example 2
The present embodiment provides a complete process assembly plate detection workbench, as shown in fig. 3, which includes:
the two-dimensional high-speed motion control platform comprises a main body frame 1, wherein a vertical guide rail is arranged on the main body frame 1, and a detection workbench 2 is movably installed in the vertical guide rail. The front of the detection workbench 2 is provided with a feeding conveying belt 3, and the rear is provided with a first discharging conveying belt 4 and a second discharging conveying belt 5 which are respectively used for delivering defective products and good products.
Above the feed conveyor belt 3, the main body frame 1 is provided with a corresponding first guide rail 12, on which first guide rail 12 a first mechanical clamping device 61 is mounted. Correspondingly, above the first and second outfeed conveyor belts 4, 5, the main body frame 1 is provided with corresponding second guide rails 13, and the second guide rails 13 are provided with second mechanical clamping devices 62.
The central part of the detection workbench 2 is in a hollowed-out design, a third guide rail and a fourth guide rail are respectively arranged above and below the detection workbench 2 on the corresponding main body frame 1, a first high-definition industrial camera and a first laser ranging module are movably installed on the third guide rail, a second high-definition industrial camera and a second laser ranging module are movably installed on the fourth guide rail, and the second high-definition industrial camera and the second laser ranging module are respectively used for photographing and ranging the upper surface and the lower surface of a to-be-detected assembly plate arranged on the detection workbench 2.
The whole detection workbench is also provided with a control host.
As a preferred implementation, the control host is an embedded intelligent processor and comprises a drive control module and an information processing module.
The driving control module comprises an embedded motion control component taking a DSP chip as a core, a transmission driving motor for respectively and electrically connecting a feeding transmission belt 3, a first discharging transmission belt 4 and a second discharging transmission belt 5, and a displacement driving motor for detecting the workbench 2, a first mechanical clamping device 61, a second mechanical clamping device 62, a first high-definition industrial camera, a first laser ranging module, a second high-definition industrial camera and a second laser ranging module, and is used for controlling the operation of the transmission belts and the displacement of each component on corresponding guide rails.
As a preferred embodiment, the displacement driving motor is a high-power high-precision alternating current servo motor so as to drive corresponding parts to complete high-precision displacement.
The information processing module comprises an embedded microprocessor and a memory, and is respectively in communication connection with the first high-definition industrial camera, the first laser ranging module, the second high-definition industrial camera and the second laser ranging module, and is used for receiving images or ranging information and performing corresponding processing.
As a further preferred embodiment, in this embodiment, the main body frame 1 is further provided with a man-machine interaction device, which may be a touch display screen, and is connected to the control host for controlling the instruction input and the display of the processing result.
As a further preferred embodiment, in this embodiment, the main body frame 1 is further provided with an audible and visual alarm device, such as an alarm lamp and a buzzer, and is connected to the control host for emitting an audible and visual alarm signal.
The detection workbench in the embodiment 2 can be combined with the intelligent detection method in the embodiment 1 to finish the intelligent detection of the assembly plate to be detected. The whole detection procedure is described in further detail below:
in operation, after the assembly board to be detected (KIT board) is fed by the feeding conveyor belt 3, the first clamping device 61 clamps the KIT board from the end of the feeding conveyor belt 3 to the region of the detection platform 2. And the first laser ranging module, the second laser ranging module, the first high-definition industrial camera, the second high-definition industrial camera and the KIT plate positioned on the detection platform area respectively perform Y-axis and X-axis movement, and the speeds of the first laser ranging module, the second laser ranging module, the first high-definition industrial camera and the second high-definition industrial camera are matched with each other until the laser ranging module traverses and measures three-coordinate information of all parts on the KIT plate. The information processing module of the high-definition industrial camera and the control host communicates through the Ethernet, the KIT plate picture is transmitted to the information processing module in real time, the information processing module identifies the type of the KIT plate through the KIT plate picture, the position height of a workpiece on the KIT plate is identified quickly in an auxiliary mode, and meanwhile a corresponding standard model of the assembly plate is searched. Meanwhile, an information processing module of the control host is connected and communicated with the laser ranging module through an RS232/RS485 cable, and three-dimensional high-precision imaging is carried out after the measurement data of the complete KIT plate are received, so that an accurate three-dimensional imaging model is obtained; and then, the intelligent detection method described in the embodiment 1 is adopted for intelligent detection, so that whether the assembly board to be detected is qualified or not can be judged. In addition, the control host can also mark the detection result information on the picture, and transmit all the information to the display control equipment through the Ethernet for real-time display and alarm.
By adopting the detection mode, the detection accuracy is greatly improved compared with manual detection, and the detection accuracy can reach more than 99.9%. Meanwhile, the detection efficiency is high, and the time for detecting the single KIT plate is about 5 minutes under the condition that only one pair of displacement laser ranging modules are installed; the system also has expandability, and the detection efficiency can be further improved by increasing the number of the displacement laser ranging modules.
The above description of the embodiments is only for aiding in the understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (6)
1. The intelligent detection method of the complete process assembly plate is characterized by comprising the following steps of:
s1, collecting image information of a to-be-detected assembly plate, and identifying the type of the to-be-detected assembly plate and a position area of a workpiece on the assembly plate based on the image information;
s2, carrying out precise laser ranging on the position area based on the identification information in the S1, and searching a standard model of the assembly plate matched with the assembly plate to be detected;
s3, performing three-dimensional imaging on the to-be-detected assembly plate through a point cloud imaging algorithm based on the precise laser ranging data, acquiring a precise three-dimensional imaging model of the to-be-detected assembly plate, and positioning a workpiece;
s4, calling the standard model of the assembly plate to be matched with the accurate three-dimensional imaging model, and detecting the sizes, shapes and positions of all workpieces on the accurate three-dimensional imaging model to judge whether the assembly plate to be detected corresponding to the accurate three-dimensional imaging model is qualified or not, wherein the method specifically comprises the following steps of:
s41, placing the standard model of the assembly plate and the accurate three-dimensional imaging model in a coordinate space with a scanning plane of an XOY plane and a scanning height value of Z, wherein each pixel point in the model is represented by an (x, y, Z) vector;
s42, performing equal area division on the area of the model in the XOY scanning plane, dividing the area into L small areas, and calculating the central position of each small area to obtain a value vector p of a central point i ＝(x i ,y i ,z i ) I=1, 2..l, the value vectors of all the center points constitute a center point value vector set;
s43, for each center point p i Order-makingFor point p i The corresponding covariance matrix of the neighbor point set is shown in the following formula:
wherein ,is->Is defined by the center of gravity of (2); let lambda get 1 ,λ 2 ,λ 3 Is 3 eigenvalues of C and satisfies lambda 1 ≥λ 2 ≥λ 3 Then p is i The corresponding normal vector is lambda 3 Corresponding feature vectors, and further obtain p i Corresponding normal vector n i I.e. matching pairs: (p) i ,n i )；
S44, matching any two points in the vector set of the central point of the standard model of the assembly plateMatching pair +.A matching pair of any two points in the vector set of the central point value of the accurate three-dimensional imaging model>Respectively calculating the distance between the two points and the normal vector included angle:
and />
And the calculated result is compared with a preset geometric rigidity threshold tau dist And a normal vector shift threshold τ angle Comparing;
s45, if the matching pair of any two points in the accurate three-dimensional imaging model center point value vector set and the matching pair of any two points in the assembly plate standard model center point value vector set meet the following conditions:
|d S -d T |＜τ dist
|θ S -θ T |＜τ angle
the accurate three-dimensional imaging model is deemed to match the mounting plate standard model.
2. A complete process assembly plate inspection station utilizing the complete process assembly plate intelligent inspection method of claim 1, comprising:
the system comprises a two-dimensional high-speed motion control platform, a high-definition industrial camera, a laser ranging module and a control host;
the two-dimensional high-speed motion control platform comprises a main body frame (1), a detection workbench (2) movably mounted on a vertical guide rail (11) in the main body frame (1), a feeding conveying belt (3) positioned in front of the detection workbench (2), and a first discharging conveying belt (4) and a second discharging conveying belt (5) positioned behind the detection workbench (2);
the main body frame (1) is provided with a first guide rail (12) above the feeding conveyor belt (3), a first mechanical clamping device (61) is movably mounted on the first guide rail (12), the main body frame (1) is provided with a second guide rail (13) above the first discharging conveyor belt (4) and the second discharging conveyor belt (5), and a second mechanical clamping device (62) is movably mounted on the second guide rail (13);
the center part of the detection workbench (2) is in a hollowed-out design, a third guide rail and a fourth guide rail are respectively arranged above and below the detection workbench (2) by the main body frame (1), a first high-definition industrial camera and a first laser ranging module are movably mounted on the third guide rail, and a second high-definition industrial camera and a second laser ranging module are movably mounted on the fourth guide rail;
the control host is electrically connected with the conveying driving motors of the feeding conveyor belt (3), the first discharging conveyor belt (4) and the second discharging conveyor belt (5) respectively, and the displacement driving motors of the detection workbench (2), the first mechanical clamping device (61), the second mechanical clamping device (62), the first high-definition industrial camera, the first laser ranging module, the second high-definition industrial camera and the second laser ranging module are used for controlling the operation of the conveyor belt and the displacement of each part on the corresponding guide rail; the control host is also respectively in communication connection with the first high-definition industrial camera, the first laser ranging module, the second high-definition industrial camera and the second laser ranging module, and is used for receiving images or ranging information and performing corresponding processing.
3. The tooling plate inspection station of claim 2 wherein the displacement drive motor is a high power high precision ac servo motor.
4. The complete process assembly plate detection workbench according to claim 2, wherein the control host is an embedded intelligent processor and comprises a drive control module and an information processing module, the drive control module comprises an embedded motion control component taking a Digital Signal Processor (DSP) chip as a core, and the information processing module comprises an embedded microprocessor and a memory.
5. The inspection workbench for complete process assembly of any of claims 2-4, wherein the main frame is further provided with a man-machine interaction device, and the man-machine interaction device is connected to the control host for controlling instruction input and display of processing results.
6. The inspection workbench for the complete process assembly plate of claim 5, wherein the main frame is further provided with an audible and visual alarm device, and the audible and visual alarm device is connected with the control host and is used for emitting audible and visual alarm signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811541923.2A CN109590952B (en) | 2018-12-17 | 2018-12-17 | Intelligent detection method and detection workbench for complete process assembly plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811541923.2A CN109590952B (en) | 2018-12-17 | 2018-12-17 | Intelligent detection method and detection workbench for complete process assembly plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109590952A CN109590952A (en) | 2019-04-09 |
| CN109590952B true CN109590952B (en) | 2023-10-13 |
Family
ID=65962944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811541923.2A Active CN109590952B (en) | 2018-12-17 | 2018-12-17 | Intelligent detection method and detection workbench for complete process assembly plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109590952B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110686594B (en) * | 2019-09-12 | 2021-08-27 | 福州国化智能技术有限公司 | Workpiece size detection method and system |
| CN111238370A (en) * | 2020-02-20 | 2020-06-05 | 中国科学院声学研究所东海研究站 | Intelligent detection method and device for KIT board |
| CN111626995B (en) * | 2020-05-19 | 2024-03-01 | 上海艾豚科技有限公司 | Intelligent insert detection method and device for workpiece |
| CN113628177A (en) * | 2021-07-29 | 2021-11-09 | 北京好运达智创科技有限公司 | Double-layer beam storage detection system for beam body |
| CN114229519B (en) * | 2021-12-30 | 2023-12-08 | 芜湖哈特机器人产业技术研究院有限公司 | Positioning device and positioning method for large material barrel |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520319A (en) * | 2008-02-27 | 2009-09-02 | 邹小平 | Composite three-dimensional laser measurement system and measurement method |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN106091922A (en) * | 2016-05-25 | 2016-11-09 | 广州市思林杰自动化科技有限公司 | A kind of method and device that workpiece is detected |
| WO2018137722A1 (en) * | 2017-01-25 | 2018-08-02 | 成都中信华瑞科技有限公司 | Detection method, apparatus, device, and computer storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7068825B2 (en) * | 1999-03-08 | 2006-06-27 | Orametrix, Inc. | Scanning system and calibration method for capturing precise three-dimensional information of objects |
-
2018
- 2018-12-17 CN CN201811541923.2A patent/CN109590952B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520319A (en) * | 2008-02-27 | 2009-09-02 | 邹小平 | Composite three-dimensional laser measurement system and measurement method |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN106091922A (en) * | 2016-05-25 | 2016-11-09 | 广州市思林杰自动化科技有限公司 | A kind of method and device that workpiece is detected |
| WO2018137722A1 (en) * | 2017-01-25 | 2018-08-02 | 成都中信华瑞科技有限公司 | Detection method, apparatus, device, and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109590952A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109590952B (en) | Intelligent detection method and detection workbench for complete process assembly plate | |
| CN111537517B (en) | Unmanned intelligent stamping defect identification method | |
| CN104596582B (en) | Automatic detecting device for backboard connector | |
| WO2015120734A1 (en) | Special testing device and method for correcting welding track based on machine vision | |
| CN105783723B (en) | Precision die surface processing accuracy detection device and method based on machine vision | |
| CN107703513B (en) | Non-contact net relative position detection method based on image processing | |
| CN113196337B (en) | Image processing device, work robot, substrate inspection device, and specimen inspection device | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN109990711B (en) | Appearance quality detection method for punched nickel-plated steel strip | |
| CN111626995B (en) | Intelligent insert detection method and device for workpiece | |
| CN111551559A (en) | LCD (liquid Crystal display) liquid crystal screen defect detection method based on multi-view vision system | |
| CN112215825A (en) | Quality analysis method and system based on machine vision in new energy battery manufacturing | |
| CN114529510B (en) | Automatic detection and classification method for cathode copper on-line quality | |
| CN115061078A (en) | Cloud platform based electric energy meter online automatic detection system and detection method thereof | |
| US11796483B2 (en) | Device for recognizing defects remaining in finished surface of product | |
| CN114581368B (en) | Bar welding method and device based on binocular vision | |
| CN111855667A (en) | Novel intelligent train inspection system and detection method suitable for metro vehicle | |
| CN203758470U (en) | Flatness detection apparatus for cell phone shielding cover | |
| CN107797517B (en) | Method and system for realizing steel belt punching processing detection by adopting machine vision | |
| CN117761060A (en) | Visual detection system and detection method thereof | |
| US11982629B2 (en) | Device for recognizing defects in finished surface of product | |
| CN214538037U (en) | Detection device | |
| CN205607332U (en) | Measuring device is striden to bridge crane crane span structure based on machine vision | |
| CN209182254U (en) | Optical detection device | |
| CN212083460U (en) | Automatic change detecting system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |