A PCM board quality inspection system

Abstract

The present invention relates to the technical field of steel plate detection, and discloses a PCM plate quality inspection system, comprising a lighting module, wherein the lighting module comprises a first lighting unit and a second lighting unit; an image acquisition module, wherein the image acquisition module acquires a steel plate image when the first lighting unit is working to define the first steel plate image information, and acquires a steel plate image when the second lighting unit is working to define the second steel plate image information; an image processing module, wherein the image processing module determines whether a first abnormal feature and a second abnormal feature exist according to a preset abnormality recognition strategy, and if the first abnormal feature exists, records the corresponding first feature information, and if the second abnormal feature exists, records the corresponding second feature information; an abnormality handling module, wherein if the first abnormal feature and / or the second abnormal feature exist, the abnormality handling module determines the abnormality type according to the preset abnormality judgment strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of steel plate detection, and in particular to a PCM plate quality inspection system. Background Art

[0002] PCM (Pre-Coated Metal) steel plate, also known as pre-coated metal steel plate, the processing flow of PCM steel plate is generally as follows: using hot-dip galvanizing as the substrate, the substrate is pre-treated on the surface, such as cleaning, degreasing, phosphating and other pre-treatment operations to improve the adhesion of the coating, and then the protective layer or decorative layer is evenly coated on the surface of the steel plate by roller coating, spraying and other methods, and the coating is fixed to form a protective layer by baking and other methods. This kind of steel plate has excellent corrosion resistance, weather resistance and aesthetics, and is widely used in construction, home appliances, automobiles and other fields.

[0003] The surface properties of PCM steel plates will affect their use. For example, bumps and concave spots will affect the surface flatness, and particles, black spots, scratches and other parts are prone to damage. Currently, industrial cameras are usually used to shoot and monitor the surface quality of PCM plates during quality inspection. However, scratches and other defects are difficult to show in the current quality inspection environment, resulting in incomplete quality inspection and requiring manual assistance. Summary of the invention

[0004] In view of the deficiencies in the prior art, the object of the present invention is to provide a PCM board quality inspection system for.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A PCM board quality inspection system includes a PCM board quality inspection device, wherein the quality inspection device is provided with a detection platform and a conveying structure, wherein the conveying structure conveys the PCM board through the detection platform at a set speed, and the PCM board quality inspection system includes

[0007] A lighting module, wherein the lighting module comprises a first lighting unit and a second lighting unit, wherein the first lighting unit and the second lighting unit have different irradiation directions, and the first lighting unit and the second lighting unit work alternately;

[0008] An image acquisition module, wherein the image acquisition module acquires an image of the steel plate when the first lighting unit is working to be defined as first steel plate image information, and acquires an image of the steel plate when the second lighting unit is working to be defined as second steel plate image information;

[0009] An image processing module, wherein the image processing module obtains the first steel plate image information and the second steel plate image information and determines whether there are first abnormal features and second abnormal features according to a preset abnormality recognition strategy, wherein the first abnormal feature is specifically a difference feature in the continuous first steel plate image information, and the second abnormal feature is specifically a difference feature in the continuous second steel plate image information. If the first abnormal feature exists, the corresponding first feature information is recorded, and if the second abnormal feature exists, the corresponding second feature information is recorded, and both the first feature information and the second feature information include abnormal feature content, abnormal location, and image shooting time;

[0010] The exception handling module obtains the first feature information and / or the second feature information and determines the type of exception according to a preset exception judgment strategy if the first exception feature and / or the second exception feature exist.

[0011] Furthermore, the anomaly identification strategy includes

[0012] sequentially acquiring continuous image information, wherein the continuous image information is specifically continuous first steel plate image information or continuous second steel plate image information;

[0013] The continuous image information is cut to obtain the panel area, wherein the panel area is specifically the area on the surface of the PCM panel in the continuous image information.

[0014] A difference image of two adjacent continuous image information panel areas is obtained, and whether the first abnormal feature or the second abnormal feature exists is determined according to the difference image.

[0015] Furthermore, the abnormality judgment strategy includes:

[0016] When the first abnormal feature is acquired, the first abnormal feature is used as the target abnormal feature, the first steel plate image information is used as the abnormal image information, and the second steel plate image information is used as the reference image information.

[0017] When the second abnormal feature is acquired, the second abnormal feature is used as the target abnormal feature, the second steel plate image information is used as the abnormal image information, and the first steel plate image information is used as the reference image information.

[0018] Determine whether there is an associated abnormal feature associated with the target abnormal feature in the reference image information. If not, the target abnormal feature is identified as a scratch defect. If an associated abnormal feature exists, the target abnormal feature is identified as a conventional defect, and the conventional defects include black spots, color differences, and concave and convex points.

[0019] Furthermore, the judgment process of the associated abnormal feature includes: obtaining target feature information of the target abnormal feature, obtaining the target abnormal area of ​​the target abnormal feature in the corresponding abnormal image information, locating the reference position on the reference image information based on the target abnormal area, judging whether there is a defect feature in the reference position area, extracting the defect feature information if there is a defect feature, comparing the defect feature information with the target feature information, and judging whether there is an associated abnormal feature if the similarity is less than a preset similarity threshold and the position difference between the two is less than a preset position difference threshold, and judging whether there is an associated abnormal feature; and judging whether there is no associated abnormal feature in the reference position area or the similarity between the defect feature information and the target feature information exceeds the preset similarity threshold or the position difference between the two exceeds the preset position difference threshold.

[0020] Furthermore, the exception handling module is configured with a target abnormal area delineation strategy, which draws several rectangular wireframes on the abnormal image information to surround the target abnormal features, selects the rectangular wireframe with the smallest area and uses the internal framed area as the pending area, matches the scaling factor based on the size of the pending area, and enlarges the pending area as the target abnormal area with the center of the pending area as the base point and the scaling factor as the scaling factor.

[0021] Furthermore, the image processing module is configured with an image sharpening strategy, and the image sharpening strategy includes:

[0022] Acquire the first steel plate image information or the second steel plate image information to define as image information to be processed,

[0023] Perform edge extraction in the image information to be processed to obtain edge features,

[0024] Divide the image area containing edge features into several sub-areas to be sharpened.

[0025] The contrast between the sharpened sub-regions is increased according to the extension direction of the edge feature to obtain the first steel plate image information or the second steel plate image information after sharpening.

[0026] Furthermore, the PCM board quality inspection system is configured with an environmental factor exclusion strategy, which includes

[0027] The image similarity of the continuous first steel plate image information or the continuous second steel plate image information is determined. If the similarity is less than a preset similarity threshold, it is determined that there is an environmental reflection error, and the quality inspection is suspended until the environmental reflection error is eliminated.

[0028] Furthermore, the environmental factor elimination strategy includes an interference elimination sub-strategy, and the interference elimination sub-strategy includes:

[0029] The exception handling module pre-stores a number of environmental reflection image information, and the environmental reflection image information is specifically an image of the environment projected on a qualified steel plate captured by the image acquisition module during normal use of the system. When it is determined that an environmental reflection error occurs, a pending reflection image is obtained. If the duration of the pending reflection image exceeds a preset duration, the corresponding pending reflection image is identified as the environmental reflection image information and stored.

[0030] Beneficial effects of the present invention:

[0031] The present invention sets two lighting units in different directions, and utilizes the first lighting unit and the second lighting unit to work alternately to obtain the first steel plate image information and the second steel plate image information under different ambient lighting, so as to eliminate the influence of the lighting direction on the defect display situation, and make the detection result more accurate; by dividing the target abnormal area and the reference position area, the recognition amount is reduced, the data processing speed is improved, and it is convenient to quickly locate the area where errors may occur, and the type of defects, including color difference, black spots, concave-convex spots or scratches, is judged by comparing the two areas, with a high degree of automation and a high degree of accuracy in judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the system architecture of the present invention;

[0033] Figure 2 It is a flowchart of the abnormality identification strategy in the present invention;

[0034] Figure 3 It is a flow chart of the abnormality judgment strategy in the present invention;

[0035] Figure 4 It is a flow chart of the image sharpening strategy in the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a component centered. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a component centered. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a component centered. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0039] like Figures 1 to 4 As shown, a PCM board quality inspection system of this embodiment includes providing a PCM board quality inspection device, wherein the quality inspection device is provided with a detection platform and a conveying structure, and the conveying structure conveys the PCM board through the detection platform at a set speed. The PCM board quality inspection device is specifically a device conventionally used in the prior art, and the present application does not improve the device itself, so it is not described in detail herein.

[0040] The PCM board quality inspection system includes

[0041] The lighting module includes a first lighting unit and a second lighting unit, the first lighting unit and the second lighting unit have different illumination directions, and the first lighting unit and the second lighting unit work alternately; specifically, there is no restriction on the specific illumination directions of the first lighting unit and the second lighting unit, and it is only necessary to ensure that the light emitting directions are different.

[0042] An image acquisition module, wherein the image acquisition module acquires an image of the steel plate when the first lighting unit is working to be defined as first steel plate image information, and acquires an image of the steel plate when the second lighting unit is working to be defined as second steel plate image information;

[0043] An image processing module, wherein the image processing module obtains the first steel plate image information and the second steel plate image information and determines whether there are first abnormal features and second abnormal features according to a preset abnormality recognition strategy, wherein the first abnormal feature is specifically a difference feature in the continuous first steel plate image information, and the second abnormal feature is specifically a difference feature in the continuous second steel plate image information. If the first abnormal feature exists, the corresponding first feature information is recorded, and if the second abnormal feature exists, the corresponding second feature information is recorded, and both the first feature information and the second feature information include abnormal feature content, abnormal location, and image shooting time;

[0044] The exception handling module determines the type of exception according to a preset exception judgment strategy if the first exception feature and / or the second exception feature exists.

[0045] The specific means of obtaining abnormal features based on the difference image include:

[0046] The difference image is obtained, and the pixel value of each pixel area of ​​the difference image is identified. If the pixel value fluctuates beyond a preset range, it is considered that an abnormal feature exists, and the area is used as an abnormal feature area. The abnormal feature obtained in the difference image corresponding to the first plate surface image information is the first abnormal feature; the abnormal feature obtained in the difference image corresponding to the second plate surface image information is the second abnormal feature.

[0047] The present invention sets two lighting units in different directions, and uses the first lighting unit and the second lighting unit to work alternately to obtain the first steel plate image information and the second steel plate image information under different ambient lighting, so as to eliminate the influence of the lighting direction on the defect display, so that the detection result is more accurate.

[0048] Furthermore, the anomaly identification strategy includes

[0049] sequentially acquiring continuous image information, wherein the continuous image information is specifically continuous first steel plate image information or continuous second steel plate image information;

[0050] The continuous image information is cut to obtain the panel area, wherein the panel area is specifically the area on the surface of the PCM panel in the continuous image information.

[0051] A difference image of two adjacent continuous image information panel areas is obtained, and whether the first abnormal feature or the second abnormal feature exists is determined according to the difference image.

[0052] The difference image can intuitively reflect the difference between the two images, and in the continuous first steel plate image information or the continuous second steel plate image information, while keeping the external ambient light consistent, the difference image between the continuous images can reflect the defects between different parts of the steel plate. Therefore, using the difference image for judgment can intuitively reflect the defects.

[0053] Furthermore, the abnormality judgment strategy includes:

[0054] When the first abnormal feature is acquired, the first abnormal feature is used as the target abnormal feature, the first steel plate image information is used as the abnormal image information, and the second steel plate image information is used as the reference image information.

[0055] When the second abnormal feature is acquired, the second abnormal feature is used as the target abnormal feature, the second steel plate image information is used as the abnormal image information, and the first steel plate image information is used as the reference image information.

[0056] Determine whether there is an associated abnormal feature associated with the target abnormal feature in the reference image information. If not, the target abnormal feature is identified as a scratch defect. If an associated abnormal feature exists, the target abnormal feature is identified as a conventional defect, and the conventional defects include black spots, color differences, and concave and convex points.

[0057] The difference between conventional defects and scratch defects is that scratches are easily affected by ambient light and may appear under a certain angle of ambient light but not under another angle of ambient light. However, defects such as color difference, black spots, and bumps are less affected by light.

[0058] Black spots are black dot features in both the first image information and the second image information; concave and convex spots are associated in different images. As the steel plate is transported, the relative position of the lamp and the steel plate changes, and the reflective location changes; particles, color difference, etc. are less affected by light; and scratches appear locally or not at all in the continuous first image information or the second image information.

[0059] Furthermore, the judgment process of the associated abnormal feature includes: obtaining target feature information of the target abnormal feature, obtaining the target abnormal area of ​​the target abnormal feature in the corresponding abnormal image information, locating the reference position on the reference image information based on the target abnormal area, judging whether there is a defect feature in the reference position area, extracting the defect feature information if there is a defect feature, comparing the defect feature information with the target feature information, and judging whether there is an associated abnormal feature if the similarity is less than a preset similarity threshold and the position difference between the two is less than a preset position difference threshold, and judging whether there is an associated abnormal feature; and judging whether there is no associated abnormal feature in the reference position area or the similarity between the defect feature information and the target feature information exceeds the preset similarity threshold or the position difference between the two exceeds the preset position difference threshold.

[0060] The target feature information includes shape, size and position in the image. The shape can be obtained through image processing. Specifically, the shape can be represented by the distribution of color values. The size can be represented by the number of pixels.

[0061] Furthermore, the abnormality handling module is configured with a target abnormal area delineation strategy, which draws several rectangular wireframes on the abnormal image information to surround the target abnormal features, selects the rectangular wireframe with the smallest area and uses the internal framed area as the pending area, matches the scaling factor based on the size of the pending area, and uses the center of the pending area as the base point and the scaling factor as the scaling factor to enlarge the pending area as the target abnormal area. The delineation of the target abnormal area here mainly takes into account that as the PCM board moves, the relative position of the scratch and the light source changes, and the appearance of the scratch may still change. Therefore, it is necessary to adjust the size of the target abnormal area to facilitate the judgment of the scratch defect.

[0062] Furthermore, the image processing module is configured with an image sharpening strategy, and the image sharpening strategy includes:

[0063] Acquire the first steel plate image information or the second steel plate image information to define as image information to be processed,

[0064] Perform edge extraction in the image information to be processed to obtain edge features,

[0065] Divide the image area containing edge features into several sub-areas to be sharpened.

[0066] The contrast between the sharpened sub-regions is increased according to the extension direction of the edge feature to obtain the first steel plate image information or the second steel plate image information after sharpening.

[0067] Furthermore, the PCM board quality inspection system is configured with an environmental factor exclusion strategy, which includes

[0068] The image similarity of the continuous first steel plate image information or the continuous second steel plate image information is determined. If the similarity is less than a preset similarity threshold, it is determined that there is an environmental reflection error, and the quality inspection is suspended until the environmental reflection error is eliminated.

[0069] The setting of the environmental factor exclusion strategy is mainly based on the consideration that the PCM board has different appearances according to the specification requirements, such as a smooth reflective surface. When people move around, the ambient light changes, and the distribution of surrounding equipment is adjusted, it will affect the collected image information, so it is necessary to avoid misjudgment caused by these factors.

[0070] Furthermore, the environmental factor elimination strategy includes an interference elimination sub-strategy, and the interference elimination sub-strategy includes:

[0071] The exception handling module pre-stores a number of environmental reflection image information, and the environmental reflection image information is specifically an image of the environment projected on a qualified steel plate captured by the image acquisition module during normal use of the system. When it is determined that an environmental reflection error occurs, a pending reflection image is obtained. If the duration of the pending reflection image exceeds a preset duration, the corresponding pending reflection image is identified as the environmental reflection image information and stored.

[0072] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A PCM board quality inspection system, characterized by: Provided is a PCM board quality inspection device, the quality inspection device is provided with a detection platform and a conveying structure, the conveying structure conveys the PCM board through the detection platform at a set speed, the PCM board quality inspection system includes A lighting module, wherein the lighting module comprises a first lighting unit and a second lighting unit, wherein the first lighting unit and the second lighting unit have different irradiation directions, and the first lighting unit and the second lighting unit work alternately; An image acquisition module, wherein the image acquisition module acquires an image of the steel plate when the first lighting unit is working to be defined as first steel plate image information, and acquires an image of the steel plate when the second lighting unit is working to be defined as second steel plate image information; An image processing module, wherein the image processing module obtains the first steel plate image information and the second steel plate image information and determines whether there are first abnormal features and second abnormal features according to a preset abnormality recognition strategy, wherein the first abnormal feature is specifically a difference feature in the continuous first steel plate image information, and the second abnormal feature is specifically a difference feature in the continuous second steel plate image information. If the first abnormal feature exists, the corresponding first feature information is recorded, and if the second abnormal feature exists, the corresponding second feature information is recorded, and both the first feature information and the second feature information include abnormal feature content, abnormal location, and image shooting time; an exception handling module, wherein if the first exception feature and / or the second exception feature exists, the exception handling module obtains the first feature information and / or the second feature information and determines the type of the exception according to a preset exception judgment strategy; The anomaly identification strategy includes sequentially acquiring continuous image information, wherein the continuous image information is specifically continuous first steel plate image information or continuous second steel plate image information; The continuous image information is cut to obtain the panel area, wherein the panel area is specifically the area on the surface of the PCM panel in the continuous image information. Obtaining a difference image of two adjacent continuous image information panel areas, and judging whether a first abnormal feature or a second abnormal feature exists according to the difference image; The abnormality judgment strategy includes: When the first abnormal feature is acquired, the first abnormal feature is used as the target abnormal feature, the first steel plate image information is used as the abnormal image information, and the second steel plate image information is used as the reference image information. When the second abnormal feature is acquired, the second abnormal feature is used as the target abnormal feature, the second steel plate image information is used as the abnormal image information, and the first steel plate image information is used as the reference image information. Determine whether there is an associated abnormal feature associated with the target abnormal feature in the reference image information. If not, the target abnormal feature is identified as a scratch defect. If an associated abnormal feature exists, the target abnormal feature is identified as a conventional defect, and the conventional defects include black spots, color differences, and concave and convex points.

2. The PCM board quality inspection system according to claim 1, characterized in that: The judgment process of the associated abnormal feature includes: obtaining target feature information of the target abnormal feature, obtaining the target abnormal area of ​​the target abnormal feature in the corresponding abnormal image information, locating the reference position on the reference image information based on the target abnormal area, judging whether there is a defect feature in the reference position area, extracting the defect feature information if there is a defect feature, comparing the defect feature information with the target feature information, and judging whether there is an associated abnormal feature if the similarity is less than a preset similarity threshold and the position difference between the two is less than a preset position difference threshold, and judging whether there is an associated abnormal feature; if there is no defect feature in the reference position area or the similarity between the defect feature information and the target feature information exceeds the preset similarity threshold or the position difference between the two exceeds the preset position difference threshold, judging whether there is no associated abnormal feature.

3. The PCM board quality inspection system according to claim 2, characterized in that: The exception handling module is configured with a target abnormal area delineation strategy, which draws several rectangular wireframes on the abnormal image information to surround the target abnormal features, selects the rectangular wireframe with the smallest area and uses the internal framed area as the pending area, matches the scaling factor based on the size of the pending area, and enlarges the pending area as the target abnormal area with the center of the pending area as the base point and the scaling factor as the scaling factor.

4. The PCM board quality inspection system according to claim 1, characterized in that: The image processing module is configured with an image sharpening strategy, and the image sharpening strategy includes: Acquire the first steel plate image information or the second steel plate image information to define as image information to be processed, Perform edge extraction in the image information to be processed to obtain edge features, Divide the image area containing edge features into several sub-areas to be sharpened. The contrast between the sharpened sub-regions is increased according to the extension direction of the edge feature to obtain the first steel plate image information or the second steel plate image information after sharpening.

5. The PCM board quality inspection system according to claim 1, characterized in that: The PCM board quality inspection system is configured with an environmental factor exclusion strategy, which includes The image similarity of the continuous first steel plate image information or the continuous second steel plate image information is determined. If the similarity is less than a preset similarity threshold, it is determined that there is an environmental reflection error, and the quality inspection is suspended until the environmental reflection error is eliminated.

6. The PCM board quality inspection system according to claim 5, characterized in that: The environmental factor elimination strategy includes an interference elimination sub-strategy, and the interference elimination sub-strategy includes: The exception handling module pre-stores a number of environmental reflection image information, and the environmental reflection image information is specifically an image of the environment projected on a qualified steel plate captured by the image acquisition module during normal use of the system. When it is determined that an environmental reflection error occurs, a pending reflection image is obtained. If the duration of the pending reflection image exceeds a preset duration, the corresponding pending reflection image is identified as the environmental reflection image information and stored.

Images