Deep learning based classification of solder defects on printed circuit boards

In the production processes of electronic devices, production activities are interrupted due to the problems caused by soldering defects during the assembly of surface-mounted elements on printed circuit boards (PCBs) and this leads to an increase in production costs. In cream solder applications, defects that may occur in electronic cards are usually noticed at the last stage of the production process. This situation reduces the efficiency of production and causes delays in the delivery schedule of critical systems. In this study, an optimization-based deep learning model is proposed by using image-processing techniques in order to detect cream solder defects on PCBs with high performance at an early stage. Convolutional neural network (CNN), one of the deep learning methods, , is trained using the data set obtained for this study and ped regions on PCB are classified. A total of six types of classes used in the study consist of uncorrectable soldering, missing soldering, excess soldering, short circuit, undefined object and correct soldering, which are frequently used in the literature. The validity of the model has been tested on the data set consisting of 648 test data. Also, in the study, the effect of image processing and optimization methods on model performance is examined and 96.40% success rate was achieved. With the help of the proposed model, defective cream solder areas on PCBs are detected and these regions are visualized by taking them into a frame.