A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection

A Sliding-Window Principal Component thermography reconstruction approach for enhancement and identification of electronic components internal structure

“…As a result, the established 3D models of Group A and B are presented in Figure 15 4. The FEM theory and the pulse profile of the PT simulation are presented in the previous paper [22] in details.…”

“…Due to the complex lateral structure of die, mould and lead frame been stacked into a narrow space inside the ECs, the structure reconstruction using PT thermal signal challenges the conventional analysis technique. Several studies have proposed methods to identify the counterfeit sample from thermal time-domain signals using PT inspection [21,22]. However, they can not clarify exactly what the internal structure difference is.…”

“…Another promising method is Principal Component Thermography (PCT) [25,26] that uses Principal Component Analysis (PCA) in a 3D thermographic image sequence. The timedomain feature from PCA has been used for counterfeit identification in ECs [22,27,28]. PCT is a statistical tool used for identification of specific image patterns in thermograms, depicting similarities and differences of specific patterns by decomposing data to singular modes.…”

A Novel Inspection Technique for Electronic Components Using Thermography (NITECT)

“…In addition, for the large quantity inspection scenario, variation and uncertainty of heating uniformity, external pins and surface marking between chips have a strong impact on the test accuracy which should be taken into account. Compared to the deterministic decision-making, AI-based decision-making strategy can provide a rapid and robust detection against uncertainty and variation between ECs [ 27 , 28 , 29 ]. The corresponding strategy can seamlessly set a powerful foundation for detection decision making for this research.…”