Abstract. Electrical assemblies are the core of many electronic devices and therefore represent a crucial part of the overall product, which must be carefully checked before integration into its functional environment. For this reason, automatic optical inspection systems are required in electronic manufacturing to detect visible errors in products at an early stage. In particular, the automotive electronics production area is one of the sectors in which quality assurance has uppermost priority, as undetected defects can pose a danger to life. However, most optical inspection processes still have error slippage rates, which are responsible for delivering faulty electrical assemblies to customers. Therefore, this article shows how an application strategy of deep learning, based on neural networks, can be combined with an automatic optical inspection system to
further increase the recognition accuracy of the process. The additional use of artificial intelligence supported classification systems provides a way to find out the exact details about the manufacturing-related errors of electrical assemblies. However, due to the
high number of different error categories, a single classification algorithm
is usually not sufficient to provide reliable visual inspection results with
high robustness against error slip. For this reason, a hierarchical model
with multiple classifiers is proposed in this article. The principle is
based on the hierarchical description of the quality status and fault types
using several combined neural networks. In this context, the original
classification task is distributed over different subnetworks. These
subnetworks, which interact as an overall model, only verify certain error
and quality features of the electrical assemblies, which means that higher
recognition accuracy and robustness can be achieved compared to a single
network.
Accuracy Analysis of Alignment Methods based on Reference Features for Robot-Based Optical Inspection Systems