Technical Library | 2021-11-22 20:44:44.0
Many automated optical inspection (AOI) companies use supervised object detection networks to inspect items, a technique which expends tremendous time and energy to mark defectives. Therefore, we propose an AOI system which uses an unsupervised learning network as the base algorithm to simultaneously generate anomaly alerts and reduce labeling costs. This AOI system works by deploying the GANomaly neural network and the supervised network to the manufacturing system. To improve the ability to distinguish anomaly items from normal items in industry and enhance the overall performance of the manufacturing process, the system uses the structural similarity index (SSIM) as part of the loss function as well as the scoring parameters. Thus, the proposed system will achieve the requirements of smart factories in the future (Industry 4.0).
Technical Library | 2024-04-29 21:39:52.0
In this paper, we develop and put into practice an Automatic Optical Inspection (AOI) system based on machine vision to check the holes on a printed circuit board (PCB). We incorporate the hardware and software. For the hardware part, we combine a PC, the three-axis positioning system, a lighting device and CCD cameras. For the software part, we utilize image registration, image segmentation, drill numbering, drill contrast, and defect displays to achieve this system. Results indicated that an accuracy of 5µm could be achieved in errors of the PCB holes allowing comparisons to be made. This is significant in inspecting the missing, the multi-hole and the incorrect location of the holes. However, previous work only focusses on one or other feature of the holes. Our research is able to assess multiple features: missing holes, incorrectly located holes and excessive holes. Equally, our results could be displayed as a bar chart and target plot. This has not been achieved before. These displays help users analyze the causes of errors and immediately correct the problems. Additionally, this AOI system is valuable for checking a large number of holes and finding out the defective ones on a PCB. Meanwhile, we apply a 0.1mm image resolution which is better than others used in industry. We set a detecting standard based on 2mm diameter of circles to diagnose the quality of the holes within 10 seconds.
| 1 |
