AOI micron-sized defect detection system and detection method thereof

Abstract

The invention discloses an AOI micron-sized defect detection system and a detection method thereof, and relates to the technical field of defect detection, the AOI micron-sized defect detection system comprises the following modules: a workpiece scanning module for scanning a workpiece to obtain a material value, performing picture shooting on the workpiece to obtain a workpiece image, and establishing a workpiece database, the material value of the workpiece and the workpiece image are included in a workpiece database; according to the scheme, the temperature value and the vibration value are obtained in the dynamic sensing module, and the dynamic coefficient is obtained in combination with the temperature value and the vibration value, so that the external temperature and vibration are conveniently detected in the workpiece defect detection process, and the influence of the temperature and vibration on the workpiece defect marking result is avoided; therefore, the false alarm rate in the detection process of the AOI system can be further reduced, the reexamination workload of workers can be further reduced, and the production efficiency can be further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and in particular to an AOI micron-level defect detection system and a detection method thereof. Background Art

[0002] AOI, or automatic optical inspection, is a device that detects common defects encountered in welding production based on optical principles. AOI is a new type of testing technology that has just emerged, but it is developing rapidly. Many manufacturers have launched AOI testing equipment. During automatic testing, the machine automatically scans the PCB through a camera, collects images, and compares the tested solder joints with the qualified parameters in the database. After image processing, defects on the PCB are checked and marked through a display or automatic mark for maintenance personnel to repair.

[0003] The AOI system has extremely high detection sensitivity during the detection process, so it has very strict requirements on the detection environment. Slight temperature changes, instrument vibrations and workpiece material reflections will be marked as defects by the AOI system, so the AOI system has a high false alarm rate. Therefore, after using the AOI system to mark the workpiece for defect detection, it is necessary to manually review the marked areas, which not only increases the workload of workers but also reduces production efficiency. For this reason, we propose an AOI micron-level defect detection system and its detection method. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides an AOI micron-level defect detection system and a detection method thereof to solve the above-mentioned problems in the prior art.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: an AOI micron-level defect detection system, comprising the following modules: A workpiece scanning module scans the workpiece to obtain the material value, takes a picture of the workpiece to obtain the workpiece image, establishes a workpiece database, and incorporates the workpiece material value and the workpiece image into the workpiece database; The dynamic sensing module obtains the temperature value and the vibration value, obtains the dynamic value through the dynamic temperature value and the dynamic vibration value, and incorporates the dynamic value of the workpiece qualified detection into the workpiece database; The abnormality identification module obtains the workpiece abnormality coefficient through the material value and the dynamic value, sets the preset threshold of the workpiece abnormality coefficient, compares the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient and gives feedback to the management personnel according to the comparison result; The defect marking module captures sample workpiece images and sample workpiece dynamic values ​​in the workpiece database according to the material value of the workpiece, performs grayscale processing on the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and marks the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value.

[0006] Preferably, the workpiece is scanned in the workpiece scanning module to obtain the material value, specifically: the glossiness of the workpiece is obtained, the reflectivity of the workpiece is obtained, the transmittance of the workpiece is obtained, and the refractive index of the workpiece is obtained, and the material value of the workpiece is obtained through the glossiness, reflectivity, refractive index and transmittance of the workpiece; The material value is calculated as follows:

[0007] Among them, Cz represents the material value, Gz represents the glossiness, Fs represents the reflectivity, Zs represents the refractive index, and Ts represents the transmittance. , , and are weights, , , , .

[0008] Preferably, the temperature value is obtained in the dynamic sensing module, specifically: Step 1: Obtain the current workpiece temperature, set a preset workpiece temperature threshold, and obtain the workpiece temperature difference by subtracting the workpiece temperature from the preset workpiece temperature threshold; Step 2: Obtain the AOI device temperature and the continuous working time of the AOI device, and obtain the device temperature by weighted summing the AOI device temperature and the continuous working time of the AOI device; Step 3: Obtain the workpiece temperature difference, obtain the device temperature, and perform weighted summation of the workpiece temperature difference and the device temperature to obtain the temperature value.

[0009] Preferably, the vibration value is obtained in the dynamic sensing module, specifically: Step 1: Mark a workpiece reference point on the workpiece before testing, mark a lens reference point on the optical lens of the AOI equipment before testing, project the lens reference point onto the workpiece surface, and measure the misalignment distance between the workpiece reference point and the lens reference point to obtain the reference distance; Step 2: During the detection process, the offset distance between the workpiece reference point and the lens reference point is obtained every 0.5 seconds to obtain multiple actual distances, and the multiple actual distances are arranged in order from small to large. The maximum value and the minimum value of the multiple actual distances are taken, and the maximum distance difference and the minimum distance difference are obtained by subtracting the maximum value of the actual distance and the minimum value of the actual distance from the reference distance, respectively. The absolute value of the maximum distance difference and the absolute value of the minimum distance difference are summed to obtain the test distance; Step 3: Get the test distance, set the vibration distance preset threshold, and obtain the vibration value by multiplying the test distance by the vibration distance preset threshold.

[0010] Preferably, the calculation method of the dynamic value in the dynamic perception module is specifically as follows:

[0011] Among them, Dt represents the dynamic value, Wd represents the temperature value, and Zd represents the vibration value. and are weights, , .

[0012] Preferably, the calculation method of the workpiece abnormality coefficient in the abnormality identification module is specifically as follows: Among them, Yc represents the abnormal coefficient, Cz represents the material value, and Dt represents the dynamic value. and are weights, , .

[0013] Preferably, in the abnormality identification module, the workpiece abnormality coefficient is compared with the preset threshold value of the workpiece abnormality coefficient and feedback is given to the management personnel according to the comparison result, specifically: Step 1: Obtain the workpiece abnormality coefficient, set the preset threshold of the workpiece abnormality coefficient, compare the size relationship between the workpiece abnormality coefficient and the preset threshold of the workpiece abnormality coefficient, if the workpiece abnormality coefficient is greater than the preset threshold of the workpiece abnormality coefficient, then execute step 2, if the workpiece abnormality coefficient is less than the preset threshold of the workpiece abnormality coefficient, then feedback to the management personnel that there is no abnormality in the detection process; Step 2: Get the dynamic value, set the dynamic value preset threshold, compare the dynamic value with the dynamic value preset threshold, if the dynamic value is greater than the dynamic value preset threshold, then feedback to the management personnel that the temperature and vibration of the detection process are abnormal, and it is recommended to re-test after debugging; if the dynamic value is less than the dynamic value preset threshold, then feedback to the management personnel that the reflection is abnormal, and it is recommended to adjust the light source position and re-test.

[0014] Preferably, in the defect marking module, the defect position is marked on the workpiece image by using the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value, specifically: Step 1: Obtain the workpiece dynamic value, obtain the sample workpiece dynamic value, obtain the dynamic difference value by subtracting the workpiece dynamic value from the sample workpiece dynamic value, set the dynamic brightness associated preset threshold value, and obtain the brightness interference fluctuation value by multiplying the dynamic difference value by the dynamic brightness associated preset threshold value; Step 2: Obtain the brightness of 10 non-marked areas of the grayscale image of the sample workpiece, average the brightness of the 10 locations to obtain the reference brightness, sum the reference brightness and the brightness interference fluctuation value to obtain the standard brightness, set the brightness fluctuation value, sum the standard brightness and the brightness fluctuation value to obtain the maximum brightness, subtract the standard brightness from the brightness fluctuation value to obtain the minimum brightness, and obtain the normal brightness range through the maximum brightness and the minimum brightness; Step 3: Measure the brightness of each pixel in the grayscale image of the workpiece, mark the pixels whose brightness is not within the normal brightness range, overlap the marked workpiece grayscale image with the workpiece image, and mark the marking point in the workpiece image to obtain the defect position.

[0015] An AOI micron-level defect detection method comprises the following steps: S1: Scan the workpiece to obtain the material value, take a picture of the workpiece to obtain the workpiece image, establish a workpiece database, and incorporate the material value and the workpiece image of the workpiece into the workpiece database; S2: Obtain temperature value, obtain vibration value, obtain dynamic value through dynamic temperature value and dynamic vibration value, and incorporate dynamic value of workpiece qualified inspection into workpiece database; S3: Obtain the workpiece abnormality coefficient through the material value and the dynamic value, set the preset threshold of the workpiece abnormality coefficient, compare the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient, and give feedback to the management personnel according to the comparison result; S4: Capture sample workpiece images and sample workpiece dynamic values ​​in a workpiece database according to the material value of the workpiece, grayscale process the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and mark the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value.

[0016] (III) Beneficial effects The present invention provides an AOI micron-level defect detection system and a detection method thereof, which have the following beneficial effects: (1) In this scheme, the abnormality perception module obtains the abnormality coefficient through the material value and the dynamic value, and compares the abnormality coefficient with the preset threshold of the abnormality coefficient, so as to judge whether there is abnormal interference in the workpiece defect detection process according to the comparison result, and then facilitate the management personnel to use the AOI system to repeat the inspection of the workpiece according to the comparison result, which is further beneficial to reduce the false alarm rate of the AOI system during the inspection process, and further beneficial to reduce the workload of workers' re-inspection; (2) In the defect marking module, this scheme detects the material value of the workpiece and captures sample workpieces with similar material values ​​in the workpiece database, and obtains the dynamic value of the sample workpiece. Through grayscale processing of the workpiece image and the sample workpiece image, the defect position is marked on the workpiece image according to the difference between the grayscale image and the dynamic values ​​of the sample workpiece and the detected workpiece. This is helpful to adjust the defect marking according to the actual situation of the dynamic value of the workpiece, which is further beneficial to reduce the false alarm rate in the AOI system detection process, and further beneficial to reduce the workload of workers' review. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of an AOI micron-level defect detection system of the present invention; Figure 2 The present invention is a flowchart of an AOI micron-level defect detection method. DETAILED DESCRIPTION

[0018] 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.

[0019] See also Figure 1-Figure 2 The present invention provides an AOI micron-level defect detection system, comprising the following modules: A workpiece scanning module scans the workpiece to obtain the material value, takes a picture of the workpiece to obtain the workpiece image, establishes a workpiece database, and incorporates the workpiece material value and the workpiece image into the workpiece database; The dynamic sensing module obtains the temperature value and the vibration value, obtains the dynamic value through the dynamic temperature value and the dynamic vibration value, and incorporates the dynamic value of the workpiece qualified detection into the workpiece database; The abnormality identification module obtains the workpiece abnormality coefficient through the material value and the dynamic value, sets the preset threshold of the workpiece abnormality coefficient, compares the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient and gives feedback to the management personnel according to the comparison result; The defect marking module captures the sample workpiece image and the sample workpiece dynamic value in the workpiece database according to the material value of the workpiece, performs grayscale processing on the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and marks the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value; The calculation method of dynamic value in the dynamic perception module is as follows:

[0020] Among them, Dt represents the dynamic value, Wd represents the temperature value, and Zd represents the vibration value. and are weights, , ; The calculation method of the workpiece abnormality coefficient in the abnormality identification module is as follows: Among them, Yc represents the abnormal coefficient, Cz represents the material value, and Dt represents the dynamic value. and are weights, , .

[0021] In this embodiment, the solution obtains the material value and the image of the workpiece in the workpiece scanning module and establishes a database, so as to facilitate the detection of the sensitive characteristics of the workpiece to light, and then facilitate the subsequent defect detection process to avoid the situation where the workpiece reflection causes the marking error, which is beneficial to reduce the false alarm rate in the AOI system detection process, and then it is beneficial to reduce the workload of workers for review, and it is also beneficial to improve production efficiency; This solution obtains temperature and vibration values ​​in the dynamic perception module, and combines the temperature and vibration values ​​to obtain a dynamic coefficient, so as to facilitate the detection of external temperature and vibration during the workpiece defect detection process, thereby helping to avoid the temperature and vibration from affecting the workpiece defect marking results, thereby further helping to reduce the false alarm rate during the AOI system detection process, thereby further helping to reduce the workload of workers' review, and further helping to improve production efficiency; In this solution, the abnormality perception module obtains the abnormality coefficient through the material value and the dynamic value, and compares the abnormality coefficient with the preset threshold of the abnormality coefficient, so as to judge whether there is abnormal interference in the workpiece defect detection process according to the comparison result, and then it is convenient for the management personnel to use the AOI system to repeat the inspection of the workpiece according to the comparison result, which is further beneficial to reduce the false alarm rate in the AOI system inspection process, and further beneficial to reduce the workload of workers' re-inspection; In the defect marking module, this solution detects the material value of the workpiece and captures sample workpieces with similar material values ​​in the workpiece database, obtains the dynamic value of the sample workpiece, processes the workpiece image and the sample workpiece image in grayscale, and then marks the defect position on the workpiece image according to the difference between the grayscale image and the dynamic values ​​of the sample workpiece and the detected workpiece, which is beneficial to adjust the defect mark according to the actual situation of the dynamic value of the workpiece, and further helps to reduce the false alarm rate in the AOI system detection process, and further helps to reduce the workload of workers' review; It is worth mentioning that the weight values ​​in this scheme can be obtained through the hierarchical analysis method, the value of the preset threshold can be obtained through the weight analysis method, and grayscale processing of images is an existing technology, and its specific operation steps will not be described in detail here.

[0022] The workpiece is scanned in the workpiece scanning module to obtain the material value, specifically: the glossiness of the workpiece is obtained, the reflectivity of the workpiece is obtained, the transmittance of the workpiece is obtained, and the refractive index of the workpiece is obtained, and the material value of the workpiece is obtained through the glossiness, reflectivity, refractive index and transmittance of the workpiece; The material value is calculated as follows:

[0023] Among them, Cz represents the material value, Gz represents the glossiness, Fs represents the reflectivity, Zs represents the refractive index, and Ts represents the transmittance. , , and are weights, , , , .

[0024] In this embodiment, the material value of the workpiece is obtained by combining the gloss, reflectivity, refractive index and transmittance of the workpiece, so as to facilitate the understanding of the sensitivity of the workpiece to light and the surface texture, which is beneficial to avoid the situation where the AOI system causes false alarms in defect detection due to the reflection of the workpiece or the complex texture, and thus helps to reduce the workload of workers' review.

[0025] Get the temperature value in the dynamic perception module, specifically: Step 1: Obtain the current workpiece temperature, set a preset workpiece temperature threshold, and obtain the workpiece temperature difference by subtracting the workpiece temperature from the preset workpiece temperature threshold; Step 2: Obtain the AOI device temperature and the continuous working time of the AOI device, and obtain the device temperature by weighted summing the AOI device temperature and the continuous working time of the AOI device; Step 3: Obtain the workpiece temperature difference, obtain the device temperature, and perform weighted summation of the workpiece temperature difference and the device temperature to obtain the temperature value.

[0026] In this embodiment, the temperature value is obtained by combining the temperature difference of the workpiece, the temperature of the equipment and the working time of the equipment, so as to facilitate the grasp of the temperature conditions of the workpiece and the equipment, thereby helping to avoid the situation where the temperature is too high and causes a false alarm of a defect, thereby helping to reduce the workload of workers for review; It is worth mentioning that the AOI equipment temperature refers to the temperature of the optical and electronic components inside the detector.

[0027] The vibration value is obtained in the dynamic perception module, specifically: Step 1: Mark a workpiece reference point on the workpiece before testing, mark a lens reference point on the optical lens of the AOI equipment before testing, project the lens reference point onto the workpiece surface, and measure the misalignment distance between the workpiece reference point and the lens reference point to obtain the reference distance; Step 2: During the detection process, the offset distance between the workpiece reference point and the lens reference point is obtained every 0.5 seconds to obtain multiple actual distances, and the multiple actual distances are arranged in order from small to large. The maximum value and the minimum value of the multiple actual distances are taken, and the maximum distance difference and the minimum distance difference are obtained by subtracting the maximum value of the actual distance and the minimum value of the actual distance from the reference distance, respectively. The absolute value of the maximum distance difference and the absolute value of the minimum distance difference are summed to obtain the test distance; Step 3: Get the test distance, set the vibration distance preset threshold, and obtain the vibration value by multiplying the test distance by the vibration distance preset threshold.

[0028] In this embodiment, reference points are marked on the workpiece and the lens, the distance between the two reference points is measured, and the vibration intensity is judged by the change in the distance between the two reference points during the detection process. This is helpful in avoiding the situation where the vibration during the detection process causes blurred image capture and false defect detection.

[0029] In the abnormality identification module, the workpiece abnormality coefficient is compared with the preset threshold of the workpiece abnormality coefficient and feedback is given to the management personnel based on the comparison results, specifically: Step 1: Obtain the workpiece abnormality coefficient, set the preset threshold of the workpiece abnormality coefficient, compare the size relationship between the workpiece abnormality coefficient and the preset threshold of the workpiece abnormality coefficient, if the workpiece abnormality coefficient is greater than the preset threshold of the workpiece abnormality coefficient, then execute step 2, if the workpiece abnormality coefficient is less than the preset threshold of the workpiece abnormality coefficient, then feedback to the management personnel that there is no abnormality in the detection process; Step 2: Get the dynamic value, set the dynamic value preset threshold, compare the dynamic value with the dynamic value preset threshold, if the dynamic value is greater than the dynamic value preset threshold, then feedback to the management personnel that the temperature and vibration of the detection process are abnormal, and it is recommended to re-test after debugging; if the dynamic value is less than the dynamic value preset threshold, then feedback to the management personnel that the reflection is abnormal, and it is recommended to adjust the light source position and re-test.

[0030] In this embodiment, by comparing the abnormal coefficient with the preset threshold of the abnormal coefficient, it is determined whether an abnormal situation occurs during the detection process, and by comparing the dynamic value with the dynamic preset threshold, it is determined whether the cause of the abnormality is reflection or vibration, which is helpful in reminding management personnel to make adjustments to the detection process, thereby avoiding false alarms of defect marking, and reducing the workload of workers' review.

[0031] In the defect marking module, the defect position is marked on the workpiece image through the sample workpiece grayscale image, the workpiece grayscale image, the sample workpiece dynamic value and the workpiece dynamic value, specifically: Step 1: Obtain the workpiece dynamic value, obtain the sample workpiece dynamic value, obtain the dynamic difference value by subtracting the workpiece dynamic value from the sample workpiece dynamic value, set the dynamic brightness associated preset threshold value, and obtain the brightness interference fluctuation value by multiplying the dynamic difference value by the dynamic brightness associated preset threshold value; Step 2: Obtain the brightness of 10 non-marked areas of the grayscale image of the sample workpiece, average the brightness of the 10 locations to obtain the reference brightness, sum the reference brightness and the brightness interference fluctuation value to obtain the standard brightness, set the brightness fluctuation value, sum the standard brightness and the brightness fluctuation value to obtain the maximum brightness, subtract the standard brightness from the brightness fluctuation value to obtain the minimum brightness, and obtain the normal brightness range through the maximum brightness and the minimum brightness; Step 3: Measure the brightness of each pixel in the grayscale image of the workpiece, mark the pixels whose brightness is not within the normal brightness range, overlap the marked workpiece grayscale image with the workpiece image, and mark the marking point in the workpiece image to obtain the defect position.

[0032] In this embodiment, the grayscale of the image is processed, and then the defects on the workpiece surface are judged according to the brightness of the grayscale image, and the size of the brightness range is affected by the dynamic value of the workpiece. This is helpful in adjusting the range of workpiece defect detection according to the dynamic value of the workpiece, thereby helping to avoid false alarms of defect marking, and thus helping to reduce the workload of workers' review.

[0033] See also Figure 1-Figure 2 The present invention provides an AOI micron-level defect detection method, comprising the following steps: S1: Scan the workpiece to obtain the material value, take a picture of the workpiece to obtain the workpiece image, establish a workpiece database, and incorporate the material value and the workpiece image of the workpiece into the workpiece database; S2: Obtain temperature value, obtain vibration value, obtain dynamic value through dynamic temperature value and dynamic vibration value, and incorporate dynamic value of workpiece qualified inspection into workpiece database; S3: Obtain the workpiece abnormality coefficient through the material value and the dynamic value, set the preset threshold of the workpiece abnormality coefficient, compare the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient, and give feedback to the management personnel according to the comparison result; S4: Capture sample workpiece images and sample workpiece dynamic values ​​in a workpiece database according to the material value of the workpiece, grayscale process the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and mark the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value.

[0034] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0035] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0036] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An AOI micron-level defect detection system, characterized in that: Includes the following modules: A workpiece scanning module scans the workpiece to obtain the material value, takes a picture of the workpiece to obtain the workpiece image, establishes a workpiece database, and incorporates the workpiece material value and the workpiece image into the workpiece database; The dynamic sensing module obtains the temperature value and the vibration value, obtains the dynamic value through the dynamic temperature value and the dynamic vibration value, and incorporates the dynamic value of the workpiece qualified detection into the workpiece database; The abnormality identification module obtains the workpiece abnormality coefficient through the material value and the dynamic value, sets the preset threshold of the workpiece abnormality coefficient, compares the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient and gives feedback to the management personnel according to the comparison result; The defect marking module captures sample workpiece images and sample workpiece dynamic values ​​in the workpiece database according to the material value of the workpiece, performs grayscale processing on the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and marks the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value.

2. The AOI micron-level defect detection system according to claim 1, characterized in that: The workpiece is scanned in the workpiece scanning module to obtain the material value, specifically: the glossiness of the workpiece is obtained, the reflectivity of the workpiece is obtained, the transmittance of the workpiece is obtained, and the refractive index of the workpiece is obtained, and the material value of the workpiece is obtained through the glossiness, reflectivity, refractive index and transmittance of the workpiece; The material value is calculated as follows: Among them, Cz represents the material value, Gz represents the glossiness, Fs represents the reflectivity, Zs represents the refractive index, and Ts represents the transmittance. , , and are weights, , , , .

3. The AOI micron-level defect detection system according to claim 1, characterized in that: Get the temperature value in the dynamic perception module, specifically: Step 1: Obtain the current workpiece temperature, set a preset workpiece temperature threshold, and obtain the workpiece temperature difference by subtracting the workpiece temperature from the preset workpiece temperature threshold; Step 2: Obtain the AOI device temperature and the continuous working time of the AOI device, and obtain the device temperature by weighted summing the AOI device temperature and the continuous working time of the AOI device; Step 3: Obtain the workpiece temperature difference, obtain the device temperature, and perform weighted summation of the workpiece temperature difference and the device temperature to obtain the temperature value.

4. The AOI micron-level defect detection system according to claim 1, characterized in that: The vibration value is obtained in the dynamic perception module, specifically: Step 1: Mark a workpiece reference point on the workpiece before testing, mark a lens reference point on the optical lens of the AOI equipment before testing, project the lens reference point onto the workpiece surface, and measure the misalignment distance between the workpiece reference point and the lens reference point to obtain the reference distance; Step 2: During the detection process, the offset distance between the workpiece reference point and the lens reference point is obtained every 0.5 seconds to obtain multiple actual distances, and the multiple actual distances are arranged in order from small to large. The maximum value and the minimum value of the multiple actual distances are taken, and the maximum distance difference and the minimum distance difference are obtained by subtracting the maximum value of the actual distance and the minimum value of the actual distance from the reference distance, respectively. The absolute value of the maximum distance difference and the absolute value of the minimum distance difference are summed to obtain the test distance; Step 3: Get the test distance, set the vibration distance preset threshold, and obtain the vibration value by multiplying the test distance by the vibration distance preset threshold.

5. The AOI micron-level defect detection system according to claim 1, characterized in that: The calculation method of dynamic value in the dynamic perception module is as follows: Among them, Dt represents the dynamic value, Wd represents the temperature value, and Zd represents the vibration value. and are weights, , .

6. The AOI micron-level defect detection system according to claim 1, characterized in that: The calculation method of the workpiece abnormality coefficient in the abnormality identification module is as follows: Among them, Yc represents the abnormal coefficient, Cz represents the material value, and Dt represents the dynamic value. and are weights, , .

7. The AOI micron-level defect detection system according to claim 1, characterized in that: In the abnormality identification module, the workpiece abnormality coefficient is compared with the preset threshold of the workpiece abnormality coefficient and feedback is given to the management personnel based on the comparison results, specifically: Step 1: Obtain the workpiece abnormality coefficient, set the preset threshold of the workpiece abnormality coefficient, compare the size relationship between the workpiece abnormality coefficient and the preset threshold of the workpiece abnormality coefficient, if the workpiece abnormality coefficient is greater than the preset threshold of the workpiece abnormality coefficient, then execute step 2, if the workpiece abnormality coefficient is less than the preset threshold of the workpiece abnormality coefficient, then feedback to the management personnel that there is no abnormality in the detection process; Step 2: Get the dynamic value, set the dynamic value preset threshold, compare the dynamic value with the dynamic value preset threshold, if the dynamic value is greater than the dynamic value preset threshold, then feedback to the management personnel that the temperature and vibration of the detection process are abnormal, and it is recommended to re-test after debugging; if the dynamic value is less than the dynamic value preset threshold, then feedback to the management personnel that the reflection is abnormal, and it is recommended to adjust the light source position and re-test.

8. The AOI micron-level defect detection system according to claim 1, characterized in that: In the defect marking module, the defect position is marked on the workpiece image through the sample workpiece grayscale image, the workpiece grayscale image, the sample workpiece dynamic value and the workpiece dynamic value, specifically: Step 1: Obtain the workpiece dynamic value, obtain the sample workpiece dynamic value, obtain the dynamic difference value by subtracting the workpiece dynamic value from the sample workpiece dynamic value, set the dynamic brightness associated preset threshold value, and obtain the brightness interference fluctuation value by multiplying the dynamic difference value by the dynamic brightness associated preset threshold value; Step 2: Obtain the brightness of 10 non-marked areas of the grayscale image of the sample workpiece, average the brightness of the 10 locations to obtain the reference brightness, sum the reference brightness and the brightness interference fluctuation value to obtain the standard brightness, set the brightness fluctuation value, sum the standard brightness and the brightness fluctuation value to obtain the maximum brightness, subtract the standard brightness from the brightness fluctuation value to obtain the minimum brightness, and obtain the normal brightness range through the maximum brightness and the minimum brightness; Step 3: Measure the brightness of each pixel in the grayscale image of the workpiece, mark the pixels whose brightness is not within the normal brightness range, overlap the marked workpiece grayscale image with the workpiece image, and mark the marking point in the workpiece image to obtain the defect position.

9. An AOI micron-level defect detection method, applied to an AOI micron-level defect detection system according to any one of claims 1 to 8, characterized in that: The steps include: S1: Scan the workpiece to obtain the material value, take a picture of the workpiece to obtain the workpiece image, establish a workpiece database, and incorporate the material value and the workpiece image of the workpiece into the workpiece database; S2: Obtain temperature value, obtain vibration value, obtain dynamic value through dynamic temperature value and dynamic vibration value, and incorporate dynamic value of workpiece qualified inspection into workpiece database; S3: Obtain the workpiece abnormality coefficient through the material value and the dynamic value, set the preset threshold of the workpiece abnormality coefficient, compare the workpiece abnormality coefficient with the preset threshold of the workpiece abnormality coefficient, and give feedback to the management personnel according to the comparison result; S4: Capture sample workpiece images and sample workpiece dynamic values ​​in a workpiece database according to the material value of the workpiece, grayscale process the workpiece image and the sample workpiece image to obtain a workpiece grayscale picture and a sample workpiece grayscale picture, and mark the defect position on the workpiece image through the sample workpiece grayscale picture, the workpiece grayscale picture, the sample workpiece dynamic value and the workpiece dynamic value.

Images