An optimal defect detection device and method for high-finish surface

By dividing the high-finished surface into small pieces and determining the optimal lighting conditions using complementary color aberration and neural network fitting, the problem of insufficient accuracy and efficiency of high-finished surface detection in the prior art is solved, and efficient and accurate crack spot detection is achieved. Improve product safety and visual quality.

CN114544659BActive Publication Date: 2024-12-06SHANGHAI INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210140450.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-16
Publication Date
2024-12-06
Estimated Expiration
2042-02-16

AI Technical Summary

Technical Problem

The existing high-quality surface crack spot detection methods and devices are insufficient in accuracy and efficiency, making it difficult to meet strict industrial inspection requirements, resulting in product safety hazards and visual perception problems.

Method used

A high-quality surface defect detection device including a detection platform, a semi-cylindrical bracket, a loading end and an evaluation end was designed. By dividing the surface into countless small pieces, using the complementary color difference method and neural network fitting, the optimal RGB lighting position was determined. , angle and brightness to quickly detect high-quality surface defects.

Benefits of technology

It significantly improves the accuracy and efficiency of inspection, reduces inspection costs, and enhances product safety and visual quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114544659B_ABST
    Figure CN114544659B_ABST
Patent Text Reader

Abstract

The present invention discloses an optimal defect detection device and method for a high-gloss surface, comprising a detection platform, a semi-cylindrical bracket, a loading end and an evaluation end, wherein the detection platform is used to place the high-gloss surface to be detected which is divided into countless small pieces; the rectangular cross-section of the semi-cylindrical bracket is placed flat on the detection platform to cover the high-gloss surface; the loading end is installed above the detection platform and inside the bottom of the semi-cylindrical bracket to irradiate the high-gloss surface with RGB lights of different positions, angles and light levels; the evaluation end is used to detect the optimal mode of each small plane by using the method of complementary chromatic aberration, and after multiple experiments, neural network fitting is used to calculate the maximum clarity of the defects on the high-gloss surface, so that the defect detection device can quickly detect the defects on the high-gloss surface in the optimal mode.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of high-finish surface defect detection, and in particular to an optimal high-finish surface defect detection device and method. Background Art

[0002] Defects, namely cracks and spots, appear on the high-gloss surface. Impurities and moisture may enter the surface, which may easily lead to impurities entering the surface and cause the cracks to expand over time. At the same time, cracks appear on the surface of some products, which may easily lead to surface rupture in the long run, causing product safety problems. Dust accumulation on the surface spots makes the product surface unclean, giving customers a bad impression.

[0003] Although there are a large number of such high-gloss surface crack spot detection methods and detection devices on the market, the detection accuracy and efficiency need to be improved. At the same time, with the development of science and technology and people's yearning for a better life, the industrial requirements for such crack spot detection are becoming more and more stringent, and experiments must be carried out from multiple aspects and angles. Therefore, it is very important to design a more efficient and accurate detection device and detection method. Summary of the invention

[0004] The purpose of the present invention is to provide a new high-finish surface detection device and detection method with higher detection efficiency and detection accuracy in view of the problems existing in the prior art.

[0005] In order to achieve the above-mentioned invention object, the technical solution adopted to solve the technical problem is as follows:

[0006] The present invention discloses a defect detection device with high finish and optimal surface quality, comprising a detection platform, a semi-cylindrical bracket, a loading end and an evaluation end, wherein:

[0007] The detection platform is used to place the high-finish surface to be detected which is divided into numerous small pieces;

[0008] The rectangular cross section of the semi-cylindrical bracket is placed flat on the detection platform to cover the high-finish surface;

[0009] The loading end is installed above the detection platform and inside the bottom of the semi-cylindrical bracket, and is used to irradiate the high-finish surface with RGB light at different positions, angles and light levels;

[0010] The evaluation end is used to detect the optimal mode of each small plane using the method of complementary chromatic aberration, and after multiple experiments, neural network fitting is used to calculate the maximum clarity of high-gloss surface defects so that the defect detection device can quickly detect defects on the high-gloss surface in the optimal mode.

[0011] Furthermore, the loading end includes a track mechanism, an RGB lighting mechanism and a driving unit, wherein:

[0012] The RGB lighting mechanism is fixed on the track mechanism and is electrically connected to the driving unit;

[0013] The driving unit is fixed on the upper part of the semi-cylindrical bracket, and is used to drive the RGB lighting mechanism and control its RGB brightness change, angle change and position change.

[0014] Furthermore, the RGB lighting mechanism is the RGB light brightness level conversion device, and the illumination levels of the three different lights R, G, and B are converted between 0-255.

[0015] Furthermore, the track mechanism is composed of a semicircular track and a linear track that constitute the semi-cylindrical bracket.

[0016] Furthermore, the high-finish surface is formed by splicing a plurality of sub-surface panels.

[0017] Furthermore, the semi-cylindrical bracket is in an opaque state for the accuracy of the experiment.

[0018] The present invention further discloses a method for detecting defects on a high-smoothness surface, which uses the above-mentioned device for detecting defects on a high-smoothness surface to perform detection, and includes the following steps:

[0019] Step S1: placing the high-finish surface to be inspected above the inspection platform and below the semi-cylindrical bracket;

[0020] Step S2: Start the driving unit to drive the RGB lighting mechanism to move along the semicircular track and the linear track to illuminate the high-gloss surface to be inspected from different angles and different positions;

[0021] Step S3: simultaneously driving the RGB illumination of the RGB illumination mechanism to change the brightness between levels 0-255, so as to irradiate the RGB light to the high-gloss surface crack defect to be detected;

[0022] Step S4: Divide the high-gloss surface into countless small blocks, and use the method of complementary color difference for each small plane to find the optimal mode. After many experiments, neural network fitting is used to find the maximum clarity of high-gloss surface defects, so as to achieve the purpose of detecting high-gloss surface defects with the optimal mode.

[0023] Further, in step S4, the optimal mode includes an optimal position, an optimal angle, and an optimal RGB lighting.

[0024] Furthermore, in step S4, a linear term plus an activation function is selected to form a nonlinear model, the unknown parameters in the model are optimally determined using a neural network algorithm, and the function model is determined using a random search method, thereby achieving a good fitting effect.

[0025] Furthermore, when the RGB illumination mechanism irradiates the high-gloss surface with light of different light levels, different positions and different angles, the clarity C has a certain functional relationship with the illumination (R, G, B), position (x, y, z) and angle (α), that is, C≈f(R, G, B, x, y, z, α), and the maximum clarity C can be obtained by neural network fitting. max .

[0026] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art:

[0027] The crack spot detection device of the present invention does not directly detect high-gloss surface defects, but divides the plane into countless small pieces, and uses the method of complementary color difference for each small plane to find the optimal mode. After multiple experiments of complementary color difference of countless small planes, that is, light level transformation, position transformation and angle transformation of RGB light, the maximum clarity is confirmed by neural network fitting, so that the position of the crack spot on the high-gloss surface being tested can be quickly determined in the optimal mode. If the product quickly detected by the optimal mode at the maximum clarity is defective, the high-gloss surface is unqualified; otherwise, it is a qualified product. The detection success rate and detection efficiency of the detection method of the present invention are greatly improved compared with the existing related detection technology, and the detection device is simple and easy to implement, which greatly reduces the detection cost and has far-reaching significance for enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0029] Figure 1 It is a schematic diagram of the overall structure of an optimal defect detection device for a high-smoothness surface according to the present invention;

[0030] Figure 2 It is a RGB illumination semicircular track model in an optimal defect detection device for a high-finish surface of the present invention;

[0031] Figure 3 It is a RGB illumination linear track model in a defect detection device with an optimal high-smoothness surface according to the present invention;

[0032] Figure 4 A schematic diagram of a structure in which defects on a high-finish surface are divided into several parts for detection in detail in an optimal defect detection device for a high-finish surface of the present invention;

[0033] Figure 5 The figure is a flow chart of an optimal defect detection method for a high-finish surface according to the present invention.

[0034]

Explanation of main symbols

[0035] 1-Detection platform;

[0036] 2-semi-cylindrical bracket;

[0037] 3-Drive unit;

[0038] 4-RGB lighting mechanism;

[0039] 5-semicircular track;

[0040] 6- Straight track;

[0041] 7-High gloss surface. DETAILED DESCRIPTION

[0042] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0043] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0044] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] Embodiment 1

[0046] like Figure 1-4 As shown, the present invention discloses a defect detection device with an optimal high-smoothness surface, comprising a detection platform 1, a semi-cylindrical bracket 2, a loading end and an evaluation end, wherein:

[0047] The detection platform 1 is used to place the high-finish surface 7 to be detected which is divided into numerous small pieces;

[0048] The rectangular cross-section of the semi-cylindrical bracket 2 is placed flat on the detection platform 1 to cover the high-finish surface 7; in this embodiment, the detection platform 1 and the semi-cylindrical bracket 2 can be placed on the experimental platform, and the detection platform 1 and the semi-cylindrical bracket 2 can be set independently or fixed together.

[0049] The loading end is installed above the detection platform 1 and inside the bottom of the semi-cylindrical bracket 2, and is used to irradiate the high-finish surface 7 with RGB light at different positions, angles and light levels;

[0050] The evaluation end is used to detect the optimal mode (optimal position, optimal angle and optimal RGB lighting) of each small plane by using the method of complementary chromatic aberration, and after multiple experiments, use neural network fitting to find the maximum clarity of defects on the high-gloss surface 7 so that the defect detection device can quickly detect defects on the high-gloss surface 7 in the optimal mode (that is, linear terms are selected plus activation functions to form a nonlinear model, the neural network algorithm is used to optimally determine the unknown parameters in the model, and the function model is determined by random search, so as to achieve a good fitting effect).

[0051] refer to Figure 2 and 3 , the loading end includes a track mechanism, an RGB lighting mechanism 4 and a driving unit 3, wherein:

[0052] The RGB lighting mechanism 4 is fixed on the track mechanism and electrically connected to the driving unit 3;

[0053] The driving unit 3 is fixed on the upper part of the semi-cylindrical bracket 2, and is used to drive the RGB lighting mechanism 4 and control its RGB brightness change, angle change and position change.

[0054] Furthermore, the RGB illumination mechanism 4 is the RGB light brightness level conversion device, and the illumination levels of the three different lights R, G, and B are converted between 0 and 255. In this embodiment, the RGB light brightness level conversion device is an RGB small lamp.

[0055] Furthermore, the track mechanism is composed of a semicircular track 5 and a linear track 6 that constitute the semi-cylindrical bracket 2.

[0056] refer to Figure 4 The high-finish surface 7 is formed by splicing a number of sub-surface panels.

[0057] Furthermore, the semi-cylindrical support 2 is in an opaque state for the accuracy of the experiment.

[0058] Embodiment 2

[0059] like Figure 5 As shown, the present invention further discloses a method for optimal defect detection of a high-smoothness surface, which uses the above-mentioned optimal defect detection device for a high-smoothness surface for detection, and includes the following steps:

[0060] Step S1: placing the high-finish surface 7 to be inspected above the inspection platform 1 and below the semi-cylindrical bracket 2;

[0061] Step S2: Start the driving unit 3 to drive the RGB illumination mechanism 4 to move along the semicircular track 5 and the linear track 6 to illuminate the high-gloss surface 7 to be inspected from different angles and different positions;

[0062] Step S3: simultaneously driving the RGB illumination of the RGB illumination mechanism 4 to change the brightness between levels 0-255, so as to irradiate the RGB light to the crack defect of the high-finish surface 7 to be detected;

[0063] Step S4: Divide the high-gloss surface 7 into countless small blocks, and use the method of complementary color difference for each small plane to find the optimal mode (optimal position, optimal angle and optimal RGB lighting). After many experiments, neural network fitting is used to calculate the maximum clarity of defects on the high-gloss surface 7, so as to achieve the purpose of detecting defects on the high-gloss surface 7 with the optimal mode.

[0064] Among them, the RGB illumination level is within 0-255, the different positions are the transformation of the RGB light running in a straight line on the linear track 6, and the different angles are the transformation of the RGB light running in a semicircular track 5 at an angle of 0-180 degrees.

[0065] Furthermore, in step S4, a linear term plus an activation function is selected to form a nonlinear model, the unknown parameters in the model are optimally determined using a neural network algorithm, and the function model is determined using a random search method, thereby achieving a good fitting effect.

[0066] Specifically, when the RGB illumination mechanism 4 irradiates the high-gloss surface 7 with light of different light levels, different positions (linear track 6) and different angles (semicircular track 5), the clarity C has a certain functional relationship with the illumination (R, G, B), position (x, y, z) and angle (α), that is, X≈f(R, G, B, x, y, z, α), and the maximum clarity C can be obtained by neural network fitting. max .

[0067] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An optimal defect detection device for high-finish surface, characterized in that: It includes a testing platform, a semi-cylindrical bracket, a loading end and an evaluation end, among which: The detection platform is used to place the high-finish surface to be detected which is divided into numerous small pieces; The rectangular cross section of the semi-cylindrical bracket is placed flat on the detection platform to cover the high-finish surface; The loading end is installed above the detection platform and inside the bottom of the semi-cylindrical bracket, and is used to irradiate the high-finish surface with RGB light at different positions, angles and light levels; The evaluation end is used to detect the optimal mode of each small plane using the method of complementary chromatic aberration, and after multiple experiments, neural network fitting is used to calculate the maximum clarity of high-gloss surface defects so that the defect detection device can quickly detect defects on the high-gloss surface in the optimal mode.

2. The defect detection device for high-smoothness surface optimization according to claim 1, characterized in that: The loading end includes a track mechanism, an RGB lighting mechanism and a driving unit, wherein: The RGB lighting mechanism is fixed on the track mechanism and is electrically connected to the driving unit; The driving unit is fixed on the upper part of the semi-cylindrical bracket, and is used to drive the RGB lighting mechanism and control its RGB brightness change, angle change and position change.

3. The defect detection device for high-smoothness surface optimization according to claim 2, characterized in that: The RGB lighting mechanism is the RGB light brightness level conversion device, and the illumination levels of the three different lights R, G, and B are converted between 0-255.

4. The defect detection device for high-smoothness surface optimization according to claim 2, characterized in that: The track mechanism is composed of a semicircular track and a linear track that constitute the semi-cylindrical bracket.

5. The defect detection device for high-smoothness surface optimization according to claim 1, characterized in that: The high-finish surface is formed by splicing a number of sub-surface panels.

6. The defect detection device for high-smoothness surface optimization according to claim 1, characterized in that: The semi-cylindrical support is in an opaque state for the accuracy of the experiment.

7. An optimal defect detection method for high-finish surface, characterized in that: The detection is performed using the optimal defect detection device for high-finish surface as described in any one of claims 1 to 6, comprising the following steps: Step S1: placing the high-finish surface to be inspected above the inspection platform and below the semi-cylindrical bracket; Step S2: Start the driving unit to drive the RGB lighting mechanism to move along the semicircular track and the linear track to illuminate the high-gloss surface to be inspected from different angles and different positions; Step S3: simultaneously driving the RGB illumination of the RGB illumination mechanism to change the brightness between levels 0-255, so as to irradiate the RGB light to the high-gloss surface crack defect to be detected; Step S4: Divide the high-gloss surface into countless small blocks, and use the method of complementary color difference for each small plane to find the optimal mode. After many experiments, neural network fitting is used to find the maximum clarity of high-gloss surface defects, so as to achieve the purpose of detecting high-gloss surface defects with the optimal mode.

8. The optimal defect detection method for high-finish surface according to claim 7, characterized in that: In step S4, the optimal mode includes an optimal position, an optimal angle, and an optimal RGB lighting.

9. The optimal defect detection device and method for high-smoothness surface according to claim 7, characterized in that: In step S4, a linear term plus an activation function is selected to form a nonlinear model, the unknown parameters in the model are optimally determined using a neural network algorithm, and the function model is determined using a random search method, thereby achieving a good fitting effect.

10. The optimal defect detection method for high-finish surface according to claim 9, characterized in that: When the RGB lighting mechanism irradiates light of different light levels, different positions and different angles onto a high-gloss surface, the clarity C has a certain functional relationship with the light (R, G, B), position (x, y, z) and angle (α), that is, C≈f(R, G, B, x, y, z, α). The maximum clarity C can be obtained by neural network fitting. max .