Abstract
Abstract. Ensuring the highest quality standards at competitive prices is one of the greatest challenges in the manufacture of electronic products. The identification of flaws has the uppermost priority in the field of automotive electronics, particularly as a failure within this field can result in damages and fatalities. During assembling and soldering of printed circuit boards (PCBs) the circuit carriers can be subject to errors. Hence, automatic optical inspection (AOI) systems are used for real-time detection of visible flaws and defects in production. This article introduces an application strategy for combining a deep learning concept with an optical inspection system based on image processing. Above all, the target is to reduce the risk of error slip through a second inspection. The concept is to have the inspection results additionally evaluated by a convolutional neural network. For this purpose, different training datasets for the deep learning procedures are examined and their effects on the classification accuracy for defect identification are assessed. Furthermore, a suitable compilation of image datasets is elaborated, which ensures the best possible error identification on solder joints of electrical assemblies. With the help of the results, convolutional neural networks can achieve a good recognition performance, so that these can support the automatic optical inspection in a profitable manner. Further research aims at integrating the concept in a fully automated way into the production process in order to decide on the product quality autonomously without human interference.
Highlights
Electrical assemblies usually represent the core of electrical devices
The major focus is on the generation of training datasets that can achieve a good recognition performance for the quality classes of the different components
It is important to avoid error slippage and pseudo errors, so that the automatic optical inspection systems can be supported in the best possible way
Summary
Electrical assemblies usually represent the core of electrical devices. the manufacturing process of most electrical assemblies is fundamentally similar and is based on the assembly and soldering of components with a printed circuit board (PCB). The quality of the assemblies can no longer be adequately assessed as part of the optical inspection This causes error slip and pseudo errors (non-genuine defects) in the test results. Another difficulty is based on the circumstances that the optical inspection can only determine the existence of defects but cannot recognize the exact type of error, such as a misplaced component. This problem results in the necessity to develop new automatic visual inspection systems. The purpose of this work is to determine which combination of training data is most suitable for the classification of an entire assembly
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
