CN116008177A - SMT component high defect identification method, system and readable medium thereof - Google Patents

Abstract

The invention discloses a method, a system and a readable medium for identifying the height defect of an SMT (surface mounted technology) component, which are characterized in that a three-dimensional point cloud model image of the SMT circuit board to be tested is obtained, and the positioning information of the SMT component on the SMT circuit board is matched and inquired through an ICP algorithm; setting a plurality of identification areas on the SMT component according to the positioning information, and acquiring the height value of each identification area according to the SMT component area relation in the three-dimensional point cloud model image; and comparing the height value of the identification area with a preset height threshold value, and judging whether the SMT component has a height defect or not. The method and the device can be used for identifying and detecting the defects of the SMT components in the height direction such as the height direction and the tilting direction, and can be used for realizing comprehensive and high-precision automatic defect detection of the SMT patch by combining the existing two-dimensional surface detection technology.

Description

SMT component height defect identification method, system and readable medium

technical field

The invention relates to the technical field of STM patching, in particular to a method, system and readable medium for identifying height defects of SMT components.

Background technique

SMT is Surface Mount Technology (Surface Mount Technology) (abbreviation of Surface Mounted Technology), which is currently the most popular technology and process in the electronics assembly industry. Electronic circuit surface assembly technology (Surface Mount Technology, SMT), known as surface mount or surface mount technology. It is a method of mounting non-pin or short-lead surface mount components (SMC/SMD for short, Chinese chip components) on the surface of a printed circuit board (PCB) or other substrates that print integrated STM components. On the surface, it is a circuit assembly technology that is soldered and assembled by methods such as reflow soldering or dip soldering.

After the emergence of SMT technology, it gradually replaced manual placement. However, some defective products will appear during the welding process of the placement machine, so the detection technology is extremely important. An efficient detection system can greatly reduce the return rate. Effectively improve the efficiency of industrial production, common SMT patch defects are divided into two categories, the first type of defects include component offset, vertical parts, foreign objects, components reversed and other defects in the 2D range; the second type of defects include component thickness error, Defects in the 3D range such as trace bending offset, trace crossing, etc. In order to detect the first type of defects, the AOI system needs to splice the obtained high-resolution SMT patch partial images in real time, and use the theoretical knowledge of machine vision to perform positioning detection on the spliced panoramic images. The principle of AOI is to irradiate the component with RGB three-color light from three different angles and then reflect it back. Different shapes of solder joints reflect different color light, and vector analysis is performed on the color and brightness of the reflected light with reference to the position and set parameters. The detection ability has certain limitations, only two-dimensional image information can be taken, and the height of components cannot be obtained.

The existing 2D detection methods are difficult to identify the height defects of SMT components, such defects will cause serious faults such as short circuit and false soldering, while 3D detection can accurately detect the height of components and solder, and then further analyze the components, It can greatly improve the accuracy of detection; therefore, it is necessary to develop a method for identifying high defects of SMT components.

Contents of the invention

The technical problem to be solved by the present invention is to provide a method, system and readable medium for identifying height defects of SMT components, aiming to solve the technical problem that the existing 2D detection means are difficult to identify the height defects of SMT components.

In order to solve the above-mentioned technical problems, the first aspect of the present invention proposes a method for identifying defects in the height of SMT components, the method comprising:

Obtain the three-dimensional point cloud model image of the SMT circuit board to be tested, and query the positioning information of the SMT components on the SMT circuit board through ICP algorithm matching;

Setting multiple identification areas on the SMT components according to the positioning information, and obtaining the height value of each identification area according to the regional relationship of the SMT components in the three-dimensional point cloud model image;

According to the comparison between the height value of the identification area and the preset height threshold, it is judged whether there is a height defect in the SMT component.

Further, the method also includes:

Pre-acquire the three-dimensional point cloud model image of the qualified SMT circuit board, and query the positioning information of the SMT components on the qualified SMT circuit board through ICP algorithm matching;

A plurality of identification areas are set on the SMT component according to the positioning information, and a height threshold of each identification area is obtained and stored according to the regional relationship of the SMT component in the three-dimensional point cloud model image.

Further, said acquisition of the three-dimensional point cloud model image of the SMT circuit board to be tested comprises:

The pictures of the SMT circuit board to be tested from different angles of view are purified by the RANSAC algorithm to obtain the feature matching points, and the feature point sets of the two point clouds are respectively So and X;

Set the number of iterations as k, let k=0, use the spatial transformation matrices Ro and To calculated by RANSAC to perform initial transformation on the purified feature point set So, and establish the Kd-tree of the feature point set X;

S ₁ =R ₀ S ₀ +T ₀ ,

Find the nearest point Sk1 of Sk in X, use the feature matching point set Sk and Sk1, calculate the coordinate transformation matrix Rk and Tk, and use the following formula to perform the coordinate transformation of the feature point set:

S _k+1 ＝R _k S _k +T _k

Determine whether the distance error D is convergent, if Dk-Dk+1<M, then converge, where M is the set threshold, and M>0, otherwise, re-find the nearest point Sk1 of Sk in X and use the feature matching point set Sk and Sk1.

Further, the feature matching points obtained by purifying the SMT circuit board graphics of different viewing angles through the RANSAC algorithm include:

Use the SIFT algorithm to perform feature matching on at least two pictures of the SMT circuit board to be tested from different viewing angles, set the threshold for judging matching to 0.6, and find N1 pairs of feature matching points;

At the same time, set an A*A recognition area, find N2 pairs of feature matching points in total, calculate the N2 pairs of feature matching points with the RANSAC algorithm, set the threshold to 0.8, that is, at least 80% of the feature points must be able to satisfy the solution The obtained rotation matrix and translation vector are obtained to obtain the rotation matrix Ro and translation vector To.

Further, according to the positioning information, multiple identification areas are set on the SMT components, and the height value of each identification area is obtained according to the regional relationship of the SMT components in the three-dimensional point cloud model image. include:

According to the positioning information, at least 4 identification areas are set up, down, left, and right on the plane of the SMT components, and all feature matches in each of the identification areas are extracted according to the regional relationship of the SMT components in the three-dimensional point cloud model image The height value of the point, and the average value of the height values of all feature matching points is used as the height value of the recognition area.

Further, comparing the height value of the identified area with the preset height threshold, judging whether there is a height defect in the SMT component includes:

Set the minimum height threshold Hl and the highest height threshold Hh of SMT components, compare the height value of the identified area with the minimum height threshold Hl and the highest height threshold Hh, if it is lower than the minimum height threshold Hl, it is judged as "the component height is low ", if it is higher than the maximum height threshold Hh, it is judged as "the component height is high".

Further, comparing the height value of the identified area with the preset height threshold, judging whether there is a height defect in the SMT component also includes:

Set the horizontal inclination angle threshold TH, obtain the horizontal inclination angle T1 according to the height difference between the identification areas in the horizontal direction of the SMT components, when the horizontal inclination angle T1 of the SMT components is greater than the horizontal inclination angle threshold TH, judged as "component horizontal tilt";

Set the vertical inclination angle threshold TV, and obtain the vertical inclination angle T2 according to the height difference between the identification areas in the vertical direction of the SMT components, when the vertical inclination angle T2 of the SMT components is greater than the The vertical tilt angle threshold TV is determined as "the component is vertically tilted".

The second aspect of the present invention proposes a SMT component height defect identification system, comprising:

A group of CCD cameras and projectors arranged on the worktable, through the CCD cameras, the light of the projector is projected onto the surface of the SMT circuit board to be tested, and the SMT circuit to be tested is obtained through the system calibration parameters and the phase-height mapping relationship 3D point cloud model image of the board;

A graphics processing terminal, receiving and storing the three-dimensional point cloud model image of the SMT circuit board to be tested, and matching and querying the location information of the SMT components on the SMT circuit board through the ICP algorithm; A plurality of identification areas are set on the component, and the height value of each identification area is obtained according to the regional relationship of the SMT component in the three-dimensional point cloud model image; according to the height value of the identification area and the preset height threshold By comparison, it is judged whether the SMT component has a high degree of defect.

Further, the system is calibrated according to the SMT structured light joint calibration model, and the relative phase is obtained by calculating the n-step phase shift of the graphics on the surface of the SMT circuit board to be tested, and the relative phase is unfolded by using the multi-frequency heterodyne phase unwrapping method to obtain Absolute phase, according to the correspondence between the absolute phase and the surface height of the SMT circuit board to be tested, the 3D point cloud model image of the SMT circuit board to be tested is obtained.

The third aspect of the present invention provides a computer-readable storage medium, which is used to store program data, and when the program data is executed by a processor, it is used to implement the method for identifying high defects of SMT components as described above.

The beneficial effects of the technical solution of the present invention:

The SMT component height defect identification method, system and readable medium of the embodiment of the present invention obtain the three-dimensional point cloud model image of the SMT circuit board to be tested, and match and query the SMT components on the SMT circuit board through the ICP algorithm Positioning information; According to the positioning information, a plurality of identification areas are set on the SMT components, and the height value of each identification area is obtained according to the regional relationship of the SMT components in the three-dimensional point cloud model image; according to The height value of the identification area is compared with a preset height threshold to determine whether there is a height defect in the SMT component. This application can realize the identification and detection of height direction defects such as height and warping of SMT components, and combined with the existing two-dimensional surface detection technology combination can realize comprehensive and high-precision automatic defect detection of SMT patches.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is a schematic flow chart of the SMT component height defect identification method of the embodiment of the present invention;

2 is a schematic flow chart of a method for establishing a height threshold in an embodiment of the present invention;

Fig. 3 is a schematic diagram of the hardware structure of the SMT component height defect identification system according to the embodiment of the present invention;

4 is a schematic diagram of a binocular camera calibration system model according to an embodiment of the present invention;

Fig. 5 is the schematic diagram of the multi-frequency heterodyne method of the embodiment of the present invention;

FIG. 6 is a schematic flow chart of a three-frequency heterodyne phase unwrapping process according to an embodiment of the present invention;

Detailed ways

The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted here that the descriptions of these embodiments are used to help understand the present invention, but are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not constitute a conflict with each other.

Example 1

As shown in Figure 1, an embodiment of the present invention provides a method for identifying a height defect of an SMT component, the method comprising:

S101. Obtain the three-dimensional point cloud model image of the SMT circuit board to be tested, and query the positioning information of the SMT components on the SMT circuit board through ICP algorithm matching;

Specifically, the acquisition of the three-dimensional point cloud model image of the SMT circuit board to be tested includes:

The pictures of the SMT circuit board to be tested from different angles of view are purified by the RANSAC algorithm to obtain the feature matching points, and the feature point sets of the two point clouds are respectively So and X;

Set the number of iterations as k, let k=0, use the spatial transformation matrices Ro and To calculated by RANSAC to perform initial transformation on the purified feature point set So, and establish the Kd-tree of the feature point set X;

S ₁ =R ₀ S ₀ +T ₀ ,

Find the nearest point Sk1 of Sk in X, use the feature matching point set Sk and Sk1, calculate the coordinate transformation matrix Rk and Tk, and use the following formula to perform the coordinate transformation of the feature point set:

S _k+1 ＝R _k S _k +T _k

Determine whether the distance error D is convergent, if Dk-Dk+1<M, then converge, where M is the set threshold, and M>0, otherwise, re-find the nearest point Sk1 of Sk in X and use the feature matching point set Sk and Sk1.

Realize the feature matching points purified by RANSAC technology, and use the ICP algorithm to perform statistical calculations. Because the initial values of the rotation matrix and translation vector established earlier have great accuracy, the ICP algorithm only obtains a more accurate rotation matrix R and translation vector T through the optimization of the initial values. In this way, the point clouds obtained from different viewing angles can be matched, and the 3D reconstruction of the 3D SMT patch and the matching of 3D components can be realized.

Specifically, the feature matching points obtained by purifying the SMT circuit board graphics of different viewing angles through the RANSAC algorithm include:

Use the SIFT algorithm to perform feature matching on at least two pictures of the SMT circuit board to be tested from different viewing angles, set the threshold for judging matching to 0.6, and find N1 pairs of feature matching points;

At the same time, set an A*A recognition area, find N2 pairs of feature matching points in total, calculate the N2 pairs of feature matching points with the RANSAC algorithm, set the threshold to 0.8, that is, at least 80% of the feature points must be able to satisfy the solution The obtained rotation matrix and translation vector are obtained to obtain the rotation matrix Ro and translation vector To.

S102. Set multiple identification areas on the SMT component according to the positioning information, and obtain the height value of each identification area according to the regional relationship of the SMT component in the three-dimensional point cloud model image;

Specifically, setting multiple identification areas on the SMT components according to the positioning information, and obtaining the height value of each identification area according to the regional relationship of the SMT components in the three-dimensional point cloud model image include:

According to the positioning information, at least 4 identification areas are set up, down, left, and right on the plane of the SMT components, and all feature matches in each of the identification areas are extracted according to the regional relationship of the SMT components in the three-dimensional point cloud model image The height value of the point, and the average value of the height values of all feature matching points is used as the height value of the recognition area.

S103. According to the comparison between the height value of the identification area and the preset height threshold, it is judged whether there is a height defect in the SMT component.

Specifically, comparing the height value of the identified area with a preset height threshold, judging whether there is a height defect in the SMT component includes:

Set the minimum height threshold Hl and the highest height threshold Hh of SMT components, compare the height value of the identified area with the minimum height threshold Hl and the highest height threshold Hh, if it is lower than the minimum height threshold Hl, it is judged as "the component height is low ", if it is higher than the maximum height threshold Hh, it is judged as "the component height is high".

Specifically, the comparison of the height value of the identified area with the preset height threshold, and judging whether there is a height defect in the SMT component also includes:

Set the horizontal inclination angle threshold TH, obtain the horizontal inclination angle T1 according to the height difference between the identification areas in the horizontal direction of the SMT components, when the horizontal inclination angle T1 of the SMT components is greater than the horizontal inclination angle threshold TH, judged as "component horizontal tilt";

Set the vertical inclination angle threshold TV, and obtain the vertical inclination angle T2 according to the height difference between the identification areas in the vertical direction of the SMT components, when the vertical inclination angle T2 of the SMT components is greater than the The vertical tilt angle threshold TV is determined as "the component is vertically tilted".

As shown in Figure 2, the method also includes:

S201. Pre-acquire the three-dimensional point cloud model image of the qualified SMT circuit board, and query the positioning information of the SMT components on the qualified SMT circuit board through ICP algorithm matching;

S202. Set multiple identification areas on the SMT component according to the positioning information, and acquire and store a height threshold of each identification area according to the area relationship of the SMT component in the 3D point cloud model image.

Example 2

As shown in Figure 3, the embodiment of the present invention also proposes a SMT component height defect identification system, including:

A group of CCD cameras 10 and projector 20 arranged on the worktable 40, through which the light of the projector 20 is projected onto the surface of the SMT circuit board 50 to be tested by the CCD cameras 10, and through the system calibration parameters and phase-height mapping Relational acquisition of the three-dimensional point cloud model image of the SMT circuit board 50 to be tested;

The graphics processing terminal 30 receives and stores the three-dimensional point cloud model image of the SMT circuit board 50 to be tested, and matches and queries the location information of the SMT components on the SMT circuit board through the ICP algorithm; A plurality of identification areas are set on the SMT components, and the height value of each identification area is obtained according to the regional relationship of the SMT components in the three-dimensional point cloud model image; according to the height value of the identification area and the preset The height threshold is compared to determine whether the SMT component has a height defect.

Among them, the system is calibrated according to the SMT structured light joint calibration model, and the relative phase is obtained by calculating the n-step phase shift of the graphics on the surface of the SMT circuit board to be tested. Phase, according to the correspondence between the absolute phase and the surface height of the SMT circuit board to be tested, the three-dimensional point cloud model image of the SMT circuit board to be tested is obtained.

Specifically, the binocular camera is used to collect the three-dimensional information of the object at the same time, and the mapping relationship between the two image coordinate systems is solved by using the parameters and other constraints between the two images. However, in this integrated system, the two belong to different coordinate systems. According to the corresponding relationship between the absolute phase and the surface height of the measured object, the three-dimensional image of the measured object can be obtained from the absolute phase.

But in this integrated system, the two belong to different coordinate systems, as shown in Figure 4, Q _L -X _L Y _L Z _L is the left camera coordinate system, Q _C -X _C Y _C Z _C is the right camera coordinate system, The conversion between the pixel point coordinates (u, v) of the left camera image plane and the coordinates (xl, yl, zl) of the marker point in the right camera coordinate system is as follows:

Among them, Φ and Δ are the rotation matrix and translation vector of the transformation of the two camera coordinate systems, and the joint calibration of the dual camera system is completed. The internal parameters of the camera can be obtained through camera calibration. Once the 3D object of each joint photographed picture is found The relationship between the point and its two-dimensional projection coordinates, that is, the world coordinates and pixel coordinates corresponding to the corner points of the chessboard, and the above formulas are used to establish the space transformation relationship, and the coordinate transformation matrix between the two cameras can be calculated.

To obtain the surface shape data of a three-dimensional object, it is necessary to project a surface structured light onto the surface of the measured object. In phase detection profile technology, a grating image whose light intensity is distributed into a standard sinusoidal distribution is generally regarded as a planar structured light path. When the grating is projected on the surface of a three-dimensional object, the projected object is modulated by the sinusoidal grating, and the light intensity shown is as follows:

Among them, Ii(x,y) is the light intensity corresponding to the i-th interference fringe, δi is the i-th phase shift amount, A(x,y) is the background light intensity, B(x,y) is the fringe Modulation depth, Φ(x, y) is the phase to be measured. A(x,y), B(x,y) and Φ(x,y) are three unknowns, so calculating Φ(x,y) requires at least three images.

Assuming that the relative displacements selected by the three grating images are: -2π/3, 0, 2π/3, then the relative light intensity expressions are:

Among them, A represents the background value of the natural light intensity of the image, and B is the background value of the projected stripe light intensity. The above formula is expanded as follows:

Further conversion is as follows:

The above is the case where the phase shift is selected as -2π/3, 0, 2π/3, and choosing an appropriate phase shift can simplify the calculation. The number of images to be collected by the three-step phase shift method is small, and the data processing speed is fast.

When we calculate the three-dimensional height information of a point, we need the absolute phase of the height of the object, but we cannot get the absolute phase of the object through the phase shift method, only the corresponding relative phase, which is discontinuous with a continuous period of 2π function. Therefore, after the relative phase is obtained, the three-dimensional information of a three-dimensional point in space cannot be directly calculated. The relative phase value needs to be processed to obtain the absolute phase value corresponding to the height information. This process is called phase unwrapping, or phase unwrapping around.

The embodiment of the present application uses the multi-frequency heterodyne phase unwrapping method to carry out the experimental calculation of phase unwrapping. The basic principle of multi-frequency heterodyne is to use different frequency phase functions Φ1(X) and Φ2 to superimpose to the lower frequency phase function Φ(X) As shown in Figure 5, where λ1, λ2, and λb are the frequencies of the phase functions Φ1(X), Φ2, and Φ(X) respectively, and λb can be calculated from λ1 and λ2 to obtain a new frequency λb:

New phase Φb:

The multi-frequency heterodyne method uses the product and difference criterion of trigonometric functions. Since the spectrum obtained by superimposition is low, the entire detection range is within the same period of the low spectrum signal, thereby determining the absolute interference phase.

Measure according to gratings of three frequencies, using gratings Φ1, Φ2, and Φ3 of three different frequencies; Obtain the final continuous absolute phase, thereby realizing the calculation from relative phase to absolute phase.

Example 3

The embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores an SMT component height defect recognition program, and when the SMT component height defect recognition program is executed by a processor, the above-mentioned SMT is realized. Steps of a method for identifying a component height defect.

It can be understood that the computer-readable storage medium in this embodiment can be applied to a server, and its specific implementation can refer to the above-mentioned embodiments, which will not be repeated here.

The SMT component height defect identification method, system and readable medium of the embodiment of the present invention obtain the three-dimensional point cloud model image of the SMT circuit board to be tested, and match and query the SMT components on the SMT circuit board through the ICP algorithm Positioning information; According to the positioning information, a plurality of identification areas are set on the SMT components, and the height value of each identification area is obtained according to the regional relationship of the SMT components in the three-dimensional point cloud model image; according to The height value of the identification area is compared with a preset height threshold to determine whether there is a height defect in the SMT component. This application can realize the identification and detection of height direction defects such as height and warping of SMT components, and combined with the existing two-dimensional surface detection technology combination can realize comprehensive and high-precision automatic defect detection of SMT patches.

Claims (10)

1. A kind of SMT components and parts height defect recognition method, it is characterized in that, described method comprises: Obtain the three-dimensional point cloud model image of the SMT circuit board to be tested, and query the positioning information of the SMT components on the SMT circuit board through ICP algorithm matching; Setting multiple identification areas on the SMT components according to the positioning information, and obtaining the height value of each identification area according to the regional relationship of the SMT components in the three-dimensional point cloud model image; According to the comparison between the height value of the identification area and the preset height threshold, it is judged whether there is a height defect in the SMT component. 2. The SMT component height defect identification method according to claim 1, is characterized in that, described method also comprises: Pre-acquire the three-dimensional point cloud model image of the qualified SMT circuit board, and query the positioning information of the SMT components on the qualified SMT circuit board through ICP algorithm matching; A plurality of identification areas are set on the SMT component according to the positioning information, and a height threshold of each identification area is obtained and stored according to the regional relationship of the SMT component in the three-dimensional point cloud model image. 3. the SMT component height defect identification method according to claim 1, is characterized in that, the three-dimensional point cloud model image that described obtaining SMT circuit board to be tested comprises: The pictures of the SMT circuit board to be tested from different angles of view are purified by the RANSAC algorithm to obtain the feature matching points, and the feature point sets of the two point clouds are respectively So and X; Set the number of iterations as k, let k=0, use the spatial transformation matrices Ro and To calculated by RANSAC to perform initial transformation on the purified feature point set So, and establish the Kd-tree of the feature point set X; S ₁ =R ₀ S ₀ +T ₀ , Find the nearest point Sk1 of Sk in X, use the feature matching point set Sk and Sk1, calculate the coordinate transformation matrix Rk and Tk, and use the following formula to perform the coordinate transformation of the feature point set: S _k+1 ＝R _k S _k +T _k Determine whether the distance error D is convergent, if Dk-Dk+1<M, then converge, where M is the set threshold, and M>0, otherwise, re-find the nearest point Sk1 of Sk in X and use the feature matching point set Sk and Sk1. 4. the SMT component height defect identification method according to claim 3, is characterized in that, described to the SMT circuit board figure to be tested of different viewing angles is purified by RANSAC algorithm and obtains feature matching point and comprises: Use the SIFT algorithm to perform feature matching on at least two pictures of the SMT circuit board to be tested from different viewing angles, set the threshold for judging matching to 0.6, and find N1 pairs of feature matching points; At the same time, set an A*A recognition area, find N2 pairs of feature matching points in total, calculate the N2 pairs of feature matching points with the RANSAC algorithm, set the threshold to 0.8, that is, at least 80% of the feature points must be able to satisfy the solution The obtained rotation matrix and translation vector are obtained to obtain the rotation matrix Ro and translation vector To. 5. The SMT component height defect recognition method according to claim 1, characterized in that, according to the positioning information, a plurality of identification areas are set on the SMT component, according to the three-dimensional point cloud model image The acquisition of the height value of each of the identification areas specifically includes: According to the positioning information, at least 4 identification areas are set up, down, left, and right on the plane of the SMT components, and all feature matches in each of the identification areas are extracted according to the regional relationship of the SMT components in the three-dimensional point cloud model image The height value of the point, and the average value of the height values of all feature matching points is used as the height value of the recognition area. 6. The method for identifying height defects of SMT components according to claim 1, characterized in that, comparing the height value of the identified area with a preset height threshold value, it is judged whether there is a height defect in the SMT components include: Set the minimum height threshold Hl and the highest height threshold Hh of SMT components, compare the height value of the identified area with the minimum height threshold Hl and the highest height threshold Hh, if it is lower than the minimum height threshold Hl, it is judged as "the component height is low ", if it is higher than the maximum height threshold Hh, it is judged as "the component height is high". 7. The method for identifying height defects of SMT components according to claim 1, characterized in that, comparing the height value of the identification area with a preset height threshold value, it is judged whether there is a height defect in the SMT components Also includes: Set the horizontal inclination angle threshold TH, obtain the horizontal inclination angle T1 according to the height difference between the identification areas in the horizontal direction of the SMT components, when the horizontal inclination angle T1 of the SMT components is greater than the horizontal inclination angle threshold TH, judged as "component horizontal tilt"; Set the vertical inclination angle threshold TV, and obtain the vertical inclination angle T2 according to the height difference between the identification areas in the vertical direction of the SMT components, when the vertical inclination angle T2 of the SMT components is greater than the The vertical tilt angle threshold TV is determined as "the component is vertically tilted". 8. A high defect identification system for SMT components, characterized in that the system comprises: A group of CCD cameras and projectors arranged on the worktable, through the CCD cameras, the light of the projector is projected onto the surface of the SMT circuit board to be tested, and the SMT circuit to be tested is obtained through the system calibration parameters and the phase-height mapping relationship 3D point cloud model image of the board; A graphics processing terminal, receiving and storing the three-dimensional point cloud model image of the SMT circuit board to be tested, and matching and querying the location information of the SMT components on the SMT circuit board through the ICP algorithm; A plurality of identification areas are set on the component, and the height value of each identification area is obtained according to the regional relationship of the SMT component in the three-dimensional point cloud model image; according to the height value of the identification area and the preset height threshold By comparison, it is judged whether the SMT component has a high degree of defect. 9. The SMT component height defect recognition system according to claim 8, characterized in that, the system is calibrated according to the SMT structured light joint calibration model, and the figure on the surface of the SMT circuit board to be measured is obtained by n-step phase shift calculation For the relative phase, the relative phase is unwrapped using the multi-frequency heterodyne phase unwinding method to obtain the absolute phase, and the three-dimensional point cloud model image of the SMT circuit board to be tested is obtained according to the correspondence between the absolute phase and the surface height of the SMT circuit board to be tested. 10. A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program data, and when the program data is executed by a processor, it is used to implement any one of claims 1-7. The steps of the SMT component height defect identification method.

Images