Research on automatic defect identification technology of electronic components

Abstract

Aiming at the problems of low efficiency and low accuracy caused by manual defect detection of electronic components, FCN, SegNet/DeconvNet and DeepLab and other deep learning technologies are studied. Using Caffe, Keras, PyTorch and other frameworks, an automatic defect identification system for electronic components is developed to distinguish qualified products from unqualified ones, so as to realize intelligent defect detection of electronic components. At the same time, the detection accuracy rate is greatly improved, and the quality of electronic components is guaranteed.

Research on software defect management and automatic repair technology

“…Defects that can be repaired with automatic repair tools still account for a small part of all defects. According to the repair results of the existing error correction tools in the common error log, all the repair tools can repair less than 30% of the whole data set [8]. The accuracy of patches generated by automatic repair tools still can't meet the requirements of industrial applications.…”